I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
,
p
p
.
1
7
21
~
1
7
30
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
3
.
pp
1
7
21
-
1
7
30
1721
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Plant disea
se
cla
ss
ificatio
n using
n
o
v
el int
eg
ra
tion o
f
deep
lea
rning
CNN
a
n
d gra
ph conv
o
luti
o
na
l net
wo
rk
s
Sa
k
a
U
m
a
M
a
hes
wa
ra
Ra
o
1
,
K
esh
et
t
i Sre
ek
a
la
2
,
P
ull
uri Sriniv
a
s
Ra
o
3
,
Na
lla
Sh
iris
h
a
4
,
G
un
na
m
Srini
v
a
s
5
,
E
rr
y
Sre
edev
i
6
1
D
e
p
a
r
t
me
n
t
o
f
C
S
E
,
S
h
r
i
V
i
sh
n
u
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
f
o
r
W
o
me
n
(
A
)
,
B
h
i
ma
v
a
r
a
m
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
S
E
,
M
a
h
a
t
ma
G
a
n
d
h
i
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
(
A
)
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
Ja
y
a
m
u
k
h
i
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
i
c
a
l
S
c
i
e
n
c
e
s,
N
a
r
sam
p
e
t
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
S
E
,
M
LR
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
I
T,
A
d
i
t
y
a
U
n
i
v
e
r
s
i
t
y
,
S
u
r
a
m
p
a
l
e
m
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
M
C
A
,
S
r
i
V
e
n
k
a
t
e
sw
a
r
a
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
Ti
r
u
p
a
t
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
27
,
2
0
2
4
R
ev
is
ed
Au
g
9
,
2
0
2
4
Acc
ep
ted
A
ug
26
,
2
0
2
4
P
lan
t
d
ise
a
se
s
p
re
se
n
t
su
b
sta
n
ti
a
l
c
h
a
ll
e
n
g
e
s
t
o
g
lo
b
a
l
a
g
ricu
lt
u
re
,
sig
n
ifi
c
a
n
t
ly
a
ffe
c
ti
n
g
c
ro
p
y
ield
s
a
n
d
jeo
p
a
rd
izin
g
fo
o
d
se
c
u
rit
y
.
Ac
c
u
ra
te
a
n
d
ti
m
e
ly
d
e
tec
ti
o
n
o
f
th
e
se
d
ise
a
se
s
is
p
a
ra
m
o
u
n
t
f
o
r
m
it
i
g
a
ti
n
g
th
e
ir
a
d
v
e
rse
e
ffe
c
ts.
Th
is
p
a
p
e
r
p
r
o
p
o
se
s
a
n
o
v
e
l
a
p
p
ro
a
c
h
f
o
r
p
la
n
t
d
ise
a
se
c
las
sifica
ti
o
n
b
y
in
teg
ra
ti
n
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
s
(C
NN
s)
a
n
d
g
ra
p
h
c
o
n
v
o
lu
ti
o
n
a
l
n
e
two
r
k
s
(G
CNs
).
Th
e
m
o
d
e
l
a
ims
t
o
e
n
h
a
n
c
e
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
b
y
le
v
e
ra
g
in
g
b
o
th
v
is
u
a
l
fe
a
tu
re
s
e
x
t
ra
c
ted
b
y
CNN
s
a
n
d
re
lati
o
n
a
l
i
n
fo
rm
a
ti
o
n
c
a
p
t
u
re
d
b
y
G
CNs
.
Us
in
g
a
Ka
g
g
le
d
a
tas
e
t
c
o
n
tain
i
n
g
ima
g
e
s
o
f
d
ise
a
se
d
a
n
d
h
e
a
lt
h
y
p
la
n
t
lea
v
e
s
fr
o
m
3
1
c
las
se
s,
in
c
lu
d
in
g
a
p
p
le,
c
o
rn
,
g
ra
p
e
,
p
e
a
c
h
,
p
e
p
p
e
r
b
e
ll
,
p
o
tat
o
,
stra
wb
e
rry
,
a
n
d
to
m
a
to
.
S
tan
d
a
lo
n
e
CNN
m
o
d
e
ls we
re
train
e
d
o
n
ima
g
e
d
a
ta fro
m
e
a
c
h
p
lan
t
ty
p
e
,
w
h
il
e
sta
n
d
a
l
o
n
e
G
CN
m
o
d
e
ls
u
ti
li
z
e
d
g
ra
p
h
-
str
u
c
tu
re
d
d
a
ta
re
p
re
se
n
ti
n
g
p
lan
t
re
latio
n
sh
i
p
s
with
in
e
a
c
h
s
u
b
se
t.
T
h
e
p
ro
p
o
se
d
in
teg
ra
ted
CNN
-
G
CN
m
o
d
e
l
c
a
p
it
a
li
z
e
s
o
n
th
e
c
o
m
p
lem
e
n
tary
stre
n
g
t
h
s
o
f
CNN
s
a
n
d
G
CN
s
to
a
c
h
iev
e
imp
ro
v
e
d
c
las
sifica
ti
o
n
p
e
rf
o
rm
a
n
c
e
.
Th
ro
u
g
h
rig
o
r
o
u
s
e
x
p
e
rime
n
tatio
n
a
n
d
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis,
th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
th
e
in
teg
ra
ted
CNN
-
G
CN
a
p
p
ro
a
c
h
wa
s
e
v
a
lu
a
ted
a
lo
n
g
sid
e
sta
n
d
a
lo
n
e
CNN
a
n
d
G
CN
m
o
d
e
ls
a
c
ro
ss
a
ll
p
lan
t
t
y
p
e
s.
R
e
su
lt
s
d
e
m
o
n
stra
ted
t
h
e
su
p
e
rio
r
it
y
o
f
t
h
e
in
teg
ra
ted
m
o
d
e
l,
h
i
g
h
li
g
h
ti
n
g
it
s
p
o
ten
ti
a
l
fo
r
e
n
h
a
n
c
i
n
g
p
la
n
t
d
ise
a
se
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
C
NN
Dee
p
lear
n
in
g
GC
N
Kag
g
le
Plan
t
d
is
ea
s
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Gu
n
n
am
Srin
iv
as
Dep
ar
tm
en
t o
f
I
T
,
Ad
ity
a
Un
i
v
er
s
ity
Su
r
am
p
alem
,
I
n
d
ia
E
m
ail:
s
r
in
iv
as.g
@
ad
ity
au
n
iv
er
s
ity
.
in
1.
I
NT
RO
D
UCT
I
O
N
Plan
t
d
is
ea
s
e
s
r
ep
r
esen
t
a
f
o
r
m
id
ab
le
ch
allen
g
e
to
g
lo
b
al
a
g
r
icu
ltu
r
e,
ex
e
r
tin
g
im
m
e
n
s
e
ec
o
n
o
m
ic
p
r
ess
u
r
es
an
d
jeo
p
ar
d
izin
g
f
o
o
d
s
ec
u
r
ity
o
n
a
g
lo
b
al
s
ca
le.
T
h
e
tim
ely
an
d
p
r
ec
is
e
id
en
tific
atio
n
o
f
th
ese
d
is
ea
s
es
p
lay
s
an
in
d
is
p
en
s
ab
le
r
o
le
in
im
p
lem
en
tin
g
p
r
o
ac
tiv
e
m
itig
atio
n
m
ea
s
u
r
es
an
d
u
p
h
o
ld
in
g
s
u
s
tain
ab
le
cr
o
p
p
r
o
d
u
ctio
n
p
r
ac
tices.
Ho
wev
er
,
tr
ad
itio
n
al
d
is
ea
s
e
d
iag
n
o
s
is
m
eth
o
d
s
p
r
e
d
o
m
in
an
tly
r
ely
o
n
m
an
u
al
v
is
u
al
in
s
p
ec
tio
n
s
c
o
n
d
u
cte
d
b
y
ag
r
ic
u
ltu
r
al
ex
p
er
ts
.
W
h
ile
th
ese
m
eth
o
d
s
h
av
e
s
er
v
ed
as
th
e
co
r
n
er
s
to
n
e
o
f
d
is
ea
s
e
m
an
ag
em
en
t
f
o
r
d
ec
ad
es,
th
e
y
ar
e
in
h
er
en
tly
p
r
o
n
e
to
lim
itatio
n
s
s
u
ch
as
b
ein
g
tim
e
-
co
n
s
u
m
in
g
,
lab
o
r
-
in
ten
s
iv
e,
an
d
s
u
s
ce
p
tib
le
to
h
u
m
an
e
r
r
o
r
.
I
n
r
ec
en
t
y
ea
r
s
,
th
e
la
n
d
s
ca
p
e
o
f
d
is
ea
s
e
d
etec
tio
n
an
d
class
if
icatio
n
h
as
u
n
d
er
g
o
n
e
a
p
ar
ad
ig
m
s
h
if
t
with
th
e
ad
v
en
t
o
f
d
e
ep
lear
n
in
g
(
DL
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
2
1
-
1
7
3
0
1722
tech
n
o
lo
g
ies.
DL
tech
n
iq
u
es,
p
ar
ticu
lar
ly
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs),
h
av
e
em
er
g
ed
as
p
o
wer
f
u
l
to
o
ls
ca
p
ab
le
o
f
r
ev
o
lu
tio
n
izi
n
g
v
ar
i
o
u
s
d
o
m
ain
s
,
in
clu
d
in
g
m
ed
ical
im
ag
in
g
an
d
o
b
ject
r
ec
o
g
n
itio
n
.
C
NNs
ex
ce
l
in
lear
n
in
g
h
ier
ar
ch
ical
r
ep
r
esen
tatio
n
s
o
f
im
ag
e
f
ea
tu
r
es,
en
ab
lin
g
th
em
to
d
is
ce
r
n
s
u
b
tle
p
atter
n
s
an
d
n
u
an
ce
s
in
v
is
u
al
d
ata.
I
n
th
e
co
n
tex
t
o
f
p
lan
t
d
is
ea
s
e
d
etec
tio
n
,
C
NNs
h
o
ld
im
m
en
s
e
p
r
o
m
is
e
f
o
r
au
to
m
atin
g
th
e
p
r
o
ce
s
s
o
f
id
en
tify
in
g
d
is
ea
s
ed
p
lan
t
tis
s
u
es
f
r
o
m
th
eir
h
ea
lth
y
co
u
n
ter
p
ar
ts
with
u
n
p
r
e
ce
d
en
ted
ac
cu
r
ac
y
an
d
ef
f
icien
c
y
.
Mo
r
eo
v
e
r
,
th
e
in
teg
r
atio
n
o
f
g
r
ap
h
co
n
v
o
lu
tio
n
al
n
etwo
r
k
s
(
GC
Ns)
in
to
th
e
r
ea
lm
o
f
p
lan
t
d
is
ea
s
e
clas
s
if
icatio
n
p
r
esen
ts
an
ex
citin
g
f
r
o
n
tier
in
ag
r
icu
ltu
r
al
r
esear
ch
.
GC
Ns
o
f
f
er
a
u
n
iq
u
e
f
r
am
ewo
r
k
f
o
r
m
o
d
elin
g
r
elatio
n
al
d
ata
an
d
ca
p
tu
r
in
g
in
tr
icate
d
ep
en
d
en
cies
am
o
n
g
in
ter
co
n
n
ec
te
d
en
titi
es,
m
ak
in
g
th
em
p
ar
ticu
lar
ly
well
-
s
u
ited
f
o
r
an
aly
zi
n
g
co
m
p
lex
ag
r
icu
l
tu
r
al
ec
o
s
y
s
tem
s
.
T
h
e
co
n
v
e
r
g
en
ce
o
f
C
NNs
an
d
GC
Ns
h
er
ald
s
a
n
ew
er
a
o
f
in
n
o
v
atio
n
in
p
lan
t d
is
ea
s
e
d
etec
tio
n
,
o
f
f
er
i
n
g
a
s
y
n
er
g
is
tic
b
l
en
d
o
f
v
is
u
al
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
r
elatio
n
al
m
o
d
e
lin
g
ca
p
ab
ilit
ies
.
Dem
ilie
[
1
]
r
esear
ch
ad
d
r
ess
e
d
DL
an
d
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
eth
o
d
s
,
n
o
ta
b
ly
C
NNs,
f
o
r
im
ag
e
id
en
tific
atio
n
an
d
class
if
icatio
n
.
C
NNs
wer
e
p
r
ef
er
r
ed
f
o
r
im
ag
e
class
if
icatio
n
b
ec
au
s
e
th
ey
au
t
o
m
atica
lly
ex
tr
ac
ted
k
ey
v
is
u
al
ch
ar
ac
te
r
is
tics
an
d
ca
p
tu
r
ed
s
p
atial
h
ier
ar
ch
ies.
Pro
b
lem
ty
p
e,
d
at
a
av
ailab
ilit
y
,
an
d
co
m
p
u
tin
g
r
eso
u
r
ce
s
d
eter
m
i
n
ed
th
e
d
ec
is
io
n
b
etwe
en
tr
a
d
itio
n
al
ML
an
d
DL
.
W
h
en
d
ata
an
d
co
m
p
u
tin
g
r
eso
u
r
ce
s
wer
e
a
b
u
n
d
an
t,
DL
,
p
ar
ticu
lar
ly
C
NNs,
p
er
f
o
r
m
e
d
b
etter
i
n
im
ag
e
id
en
tific
atio
n
an
d
class
if
icatio
n
.
Ullah
et
a
l.
[
2
]
s
u
g
g
ested
a
n
in
n
o
v
ativ
e
,
ef
f
icien
t,
an
d
lig
h
tweig
h
t
DL
ar
ch
itectu
r
e
f
o
r
p
lan
t
leaf
d
is
ea
s
e
p
r
ed
ictio
n
an
d
ca
teg
o
r
izatio
n
.
Dee
p
Plan
tNet
h
as
2
8
lear
n
t
lay
er
s
,
in
clu
d
in
g
2
5
C
o
n
V
la
y
er
s
.
A
n
ew
p
lan
t
d
is
ea
s
e
class
if
icatio
n
f
r
am
e
wo
r
k
was
d
ev
elo
p
ed
u
s
in
g
L
ea
k
y
r
ec
tifie
d
lin
ea
r
u
n
i
t
(
L
R
eL
U)
,
b
atch
n
o
r
m
aliza
tio
n
(
B
N)
,
f
ir
e
m
o
d
u
les,
an
d
a
co
m
b
in
atio
n
o
f
3
×
3
an
d
1
×
1
f
ilter
s
.
Saad
an
d
Salm
an
[
3
]
p
r
o
p
o
s
ed
Siam
ese
n
eu
r
al
n
etwo
r
k
(
S
NN)
o
n
e
-
s
h
o
t
lear
n
in
g
(
OSL)
m
eth
o
d
s
f
o
r
p
lan
t
d
is
ea
s
e
class
if
icatio
n
with
m
in
im
al
d
atasets
.
T
o
e
x
p
an
d
th
e
d
ataset,
it
u
s
ed
d
ata
a
u
g
m
en
tatio
n
a
n
d
u
s
ed
r
eg
io
n
-
b
ased
p
ict
u
r
e
s
eg
m
e
n
t
atio
n
.
Gen
er
aliza
tio
n
en
h
an
c
ed
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
-
b
ased
class
if
ier
s
f
o
r
p
r
im
a
r
y
d
iag
n
o
s
es.
OSL
with
Siam
ese
n
et
wo
r
k
s
h
a
d
f
a
r
h
ig
h
er
class
if
icatio
n
ac
cu
r
ac
y
a
n
d
f
ewe
r
m
is
tak
es
th
an
n
o
r
m
al
tr
an
s
f
er
lear
n
in
g
,
with
a
p
r
o
ce
s
s
in
g
tim
e
o
f
5
m
s
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
.
T
h
e
au
th
o
r
s
id
en
tifie
d
1
8
2
p
la
n
t
d
is
ea
s
e
d
etec
tio
n
an
d
class
if
ica
tio
n
s
tu
d
ies
u
s
in
g
k
ey
wo
r
d
s
f
r
o
m
p
ee
r
-
r
ev
iewe
d
p
u
b
licatio
n
s
b
etwe
en
2
0
1
0
an
d
2
0
2
2
in
[
4
]
.
Af
ter
titl
e,
ab
s
tr
ac
t,
c
o
n
clu
s
io
n
,
an
d
f
u
ll
tex
t
ex
cl
u
s
io
n
,
7
5
ar
ticles
wer
e
r
ev
iewe
d
.
Data
-
d
r
iv
en
m
eth
o
d
s
im
p
r
o
v
ed
p
lan
t
d
is
ea
s
e
d
iag
n
o
s
is
s
y
s
tem
p
er
f
o
r
m
a
n
ce
an
d
ac
cu
r
ac
y
,
m
a
k
in
g
th
is
s
tu
d
y
u
s
ef
u
l f
o
r
r
esear
ch
er
s
.
An
a
n
d
h
i
an
d
Sath
iam
o
o
r
th
y
[
5
]
u
s
ed
DL
-
b
ased
au
to
m
ated
r
ice
p
lan
t
d
is
ea
s
e
r
ec
o
g
n
itio
n
an
d
class
if
ic
atio
n
(
DL
-
AR
PDR
C
)
to
im
p
r
o
v
e
ac
c
u
r
ac
y
a
n
d
d
iag
n
o
s
tics
.
Pre
-
p
r
o
ce
s
s
in
g
b
eg
an
with
p
ictu
r
e
s
ca
lin
g
an
d
g
au
s
s
ian
f
ilter
(
GF)
to
in
cr
ea
s
e
im
ag
e
q
u
ality
.
Ots
u
's
th
r
esh
o
ld
-
b
ased
s
eg
m
en
tatio
n
is
o
lated
lesi
o
n
s
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
,
co
n
ce
n
tr
atin
g
o
n
th
e
ar
ea
o
f
in
ter
est.
T
o
d
is
tin
g
u
is
h
illn
ess
es,
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
(
VGG
)
-
1
9
ar
c
h
itectu
r
al
f
ea
tu
r
e
e
x
tr
ac
tio
n
a
n
d
ex
tr
em
e
g
r
a
d
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
class
if
icatio
n
wer
e
u
s
ed
.
E
x
p
er
i
m
en
tal
f
in
d
in
g
s
in
d
icate
d
th
at
DL
-
AR
PD
R
C
o
u
tp
er
f
o
r
m
ed
o
t
h
er
co
n
tem
p
o
r
ar
y
m
eth
o
d
s
.
Deg
ad
wala
et
a
l.
[
6
]
ac
cu
r
ately
d
iag
n
o
s
ed
h
o
p
p
lan
t
d
is
ea
s
es,
in
d
icatin
g
ea
r
ly
d
etec
tio
n
a
n
d
ex
ac
t
m
a
n
ag
em
e
n
t.
B
y
C
N
N
ar
ch
itectu
r
es
,
h
o
p
s
p
lan
t
d
is
ea
s
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
is
co
m
p
ar
ed
.
T
h
eir
m
eth
o
d
m
ig
h
t
au
to
m
ate
a
n
d
en
h
an
ce
h
o
p
s
p
la
n
t
d
is
ea
s
e
co
n
tr
o
l,
m
ain
tai
n
h
o
p
cr
o
p
s
u
s
tain
ab
ilit
y
an
d
q
u
ality
f
o
r
b
r
ewin
g
,
a
n
d
p
r
o
v
i
d
e
th
e
g
r
o
u
n
d
wo
r
k
f
o
r
s
im
ilar
ag
r
icu
ltu
r
al
is
s
u
es.
A
d
ee
p
C
NN
m
o
d
el
f
o
r
p
lan
t
d
is
ea
s
e
id
en
tific
atio
n
th
at
o
v
er
co
m
es
f
ield
is
s
u
es
was
p
r
o
p
o
s
ed
[
7
]
.
I
t
p
er
f
o
r
m
ed
well
o
n
th
e
Plan
tVillag
e
d
ataset,
wh
ich
in
clu
d
ed
p
ictu
r
es
o
f
1
4
h
ea
lth
y
an
d
s
ick
cr
o
p
leav
es
i
n
3
1
v
ar
ieties.
T
h
e
C
NN
m
o
d
el
h
as
9
8
%
tr
ain
in
g
an
d
9
4
%
test
ac
cu
r
ac
y
in
ex
p
er
im
en
ts
.
T
h
e
p
r
o
g
r
a
m
id
en
tifie
d
leaf
d
is
ea
s
es
ea
r
ly
,
i
n
d
icatin
g
it
m
ay
b
e
u
s
ed
f
o
r
a
g
r
icu
ltu
r
al
h
ea
lth
m
o
n
ito
r
in
g
.
Usi
n
g
o
p
tim
izatio
n
an
d
DL
,
[
8
]
b
u
ilt
a
y
o
u
o
n
ly
liv
e
o
n
ce
(
YOL
O
)
-
b
ased
l
ea
f
d
is
ea
s
e
d
etec
tio
n
a
n
d
cla
s
s
if
icatio
n
s
y
s
tem
.
Pre
-
p
r
o
ce
s
s
in
g
,
PC
FAN
f
ea
tu
r
e
m
ap
g
en
er
atio
n
,
an
d
Sh
u
f
f
le
Net/E
R
S
O
clas
s
if
icatio
n
o
p
tim
izatio
n
co
m
p
r
is
ed
th
e
f
r
am
ewo
r
k
.
FC
N
-
R
FO
id
en
tifie
d
d
is
ea
s
e
-
p
r
o
n
e
lo
ca
tio
n
s
.
On
a
cu
s
to
m
p
la
n
t
leaf
p
ictu
r
e
d
ataset,
th
e
m
o
d
el
s
u
r
p
ass
ed
ea
r
lier
m
eth
o
d
s
with
h
i
g
h
ac
cu
r
ac
y
.
T
h
ese
s
tu
d
ies
s
h
o
wed
th
at
DL
class
if
ier
s
m
ig
h
t
id
en
tif
y
leaf
d
is
ea
s
es.
R
ice,
wh
ea
t,
a
n
d
m
aize
d
atab
ases
wer
e
cr
e
ated
in
[
9
]
t
o
ad
d
r
ess
th
e
s
t
ated
p
r
o
b
le
m
s
.
T
h
e
d
atasets
ex
am
in
ed
two
b
ac
ter
ial
an
d
two
f
u
n
g
al
illn
ess
es
f
o
r
r
ice,
f
o
u
r
f
u
n
g
al
d
is
ea
s
es
f
o
r
m
aize
,
an
d
f
o
u
r
f
u
n
g
al
d
is
ea
s
es
f
o
r
wh
ea
t,
w
h
ich
d
estro
y
th
e
wh
o
le
p
la
n
t.
W
ith
co
n
s
tan
t
tr
ain
in
g
h
y
p
er
p
ar
am
eter
s
,
eig
h
t
f
in
e
-
tu
n
ed
DL
m
o
d
els
wer
e
u
s
ed
.
Pre
-
tr
ain
ed
d
ee
p
C
NN
m
o
d
els
wer
e
test
ed
u
s
in
g
E
f
f
ic
ien
tNetB
3
-
ad
ap
tiv
e
au
g
m
en
ted
DL
(
AADL
)
f
o
r
ex
ac
t
illn
ess
d
iag
n
o
s
is
[
1
0
]
.
I
t
is
s
h
o
wn
t
h
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
ca
n
p
r
o
v
i
d
e
ac
cu
r
ate,
r
ea
l
-
tim
e
a
g
r
icu
ltu
r
a
l d
is
ea
s
e
d
iag
n
o
s
is
.
T
h
e
'
Z
er
o
-
s
h
o
t tr
an
s
f
er
lear
n
i
n
g
'
ap
p
r
o
ac
h
was p
r
o
p
o
s
ed
in
[
1
1
]
to
im
p
r
o
v
e
class
if
ier
p
er
f
o
r
m
an
ce
in
to
m
ato
an
d
p
o
tato
d
atasets
wh
en
th
e
s
o
u
r
ce
d
o
m
ain
h
as
d
i
f
f
er
en
t
class
es
th
an
th
e
d
esti
n
atio
n
d
o
m
ai
n
.
C
NN
m
o
d
els,
d
ata
au
g
m
en
tatio
n
,
s
y
n
th
etic
d
ata
cr
ea
tio
n
,
an
d
s
tr
o
n
g
d
is
cr
im
in
ativ
e
lo
s
s
es
im
p
r
o
v
e
d
class
if
ier
p
er
f
o
r
m
an
ce
in
ze
r
o
-
s
h
o
t
co
n
d
itio
n
s
.
R
ash
id
et
a
l.
[
1
2
]
p
r
o
p
o
s
ed
C
NN
-
b
ased
p
r
ec
is
io
n
a
g
r
icu
ltu
r
al
d
is
ea
s
e
class
if
icatio
n
ar
ch
itectu
r
e
MM
F
-
Net.
MM
F
-
Net
im
p
r
o
v
ed
ac
cu
r
ac
y
with
R
L
-
b
l
o
ck
an
d
PL
-
b
lo
ck
1
an
d
2
m
u
lti
-
co
n
tex
tu
al
f
ea
t
u
r
es.
Fu
s
io
n
ad
ap
tiv
ely
cr
ea
te
d
th
e
f
in
al
ju
d
g
m
en
t
p
r
o
b
ab
ilit
y
s
co
r
e
,
class
if
y
in
g
m
aize
leaf
d
is
ea
s
es
with
9
9
.
2
3
%
ac
cu
r
ac
y
.
Ov
er
all,
MM
F
-
Net
s
ee
m
ed
p
r
o
m
is
in
g
f
o
r
PA
p
lan
t
leaf
d
is
ea
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
la
n
t d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
n
o
ve
l in
teg
r
a
tio
n
o
f d
ee
p
lea
r
n
in
g
…
(
S
a
ka
Uma
Ma
h
esw
a
r
a
)
1723
d
etec
tio
n
.
Ah
m
ad
et
a
l.
[
1
3
]
ev
alu
ated
p
lan
t
d
is
ea
s
e
d
etec
tio
n
DL
m
o
d
els
ac
r
o
s
s
d
atasets
an
d
s
ettin
g
s
.
Fiv
e
m
aize
f
o
liar
d
is
ea
s
e
d
atasets
wer
e
u
s
ed
to
test
DL
-
b
ased
im
ag
e
class
if
icatio
n
alg
o
r
ith
m
s
.
T
h
e
b
est
p
r
e
-
tr
ain
ed
DNN
ar
ch
itectu
r
e
f
o
r
tr
an
s
f
e
r
lear
n
in
g
was
Den
s
eNe
t1
6
9
.
Gen
er
aliza
tio
n
ac
cu
r
ac
y
was
h
ig
h
est
in
C
D&
S
R
GB
A
p
h
o
to
g
r
ap
h
s
with
o
u
t
b
ac
k
g
r
o
u
n
d
s
.
New
f
ield
an
d
la
b
d
ata
im
p
r
o
v
e
d
m
o
d
el
p
er
f
o
r
m
an
ce
,
s
u
g
g
esti
n
g
f
ield
-
d
ep
lo
y
ab
le
d
is
ea
s
e
m
an
a
g
em
en
t m
eth
o
d
s
.
A
d
ee
p
C
NN
m
o
d
el
f
o
r
p
lan
t d
is
ea
s
e
ca
teg
o
r
izatio
n
was
d
e
v
elo
p
ed
in
[
1
4
]
to
s
o
lv
e
th
ese
is
s
u
es.
T
h
e
m
o
d
el
u
s
ed
Plan
tVillag
e
p
h
o
t
o
s
o
f
1
4
h
ea
lth
y
an
d
s
ick
c
r
o
p
leav
es
d
iv
i
d
ed
i
n
to
3
8
class
if
icatio
n
s
.
T
h
e
C
NN
m
o
d
el
h
as
9
8
.
0
1
%
tr
ain
in
g
a
cc
u
r
ac
y
a
n
d
9
4
%
test
ac
cu
r
a
cy
in
e
x
p
er
im
e
n
ts
.
T
h
ese
d
ata
s
h
o
wed
th
at
th
e
m
o
d
el
was
ef
f
icien
t
f
o
r
ea
r
l
y
leaf
d
is
ea
s
e
d
etec
tio
n
.
A
SV
M
an
d
im
ag
e
p
r
o
ce
s
s
in
g
m
eth
o
d
f
o
r
g
r
a
p
e
leaf
d
is
ea
s
e
d
etec
tio
n
an
d
class
if
icatio
n
was
s
u
g
g
ested
[
1
5
]
.
I
m
ag
in
g
,
d
en
o
is
in
g
,
en
h
a
n
ce
m
en
t,
s
eg
m
en
tatio
n
,
p
r
in
cip
al
c
o
m
p
o
n
en
t
an
aly
s
is
(
PC
A
)
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
an
d
class
if
icatio
n
u
tili
zin
g
p
a
r
ticle
s
war
m
o
p
tim
izar
tio
n
(
PSO
)
SVM,
b
ac
k
p
r
o
p
ag
atio
n
n
eu
r
al
n
etwo
r
k
(
B
PNN
)
,
an
d
r
an
d
o
m
f
o
r
e
s
t
alg
o
r
ith
m
s
wer
e
p
er
f
o
r
m
ed
.
I
n
g
r
ap
e
leaf
d
is
ea
s
e
class
if
icatio
n
an
d
d
etec
tio
n
,
PS
O
SVM
p
er
f
o
r
m
ed
b
etter
.
Sam
ee
r
a
et
a
l.
[
1
6
]
ap
p
lied
v
ar
io
u
s
DL
m
o
d
els
an
d
ac
h
iv
ed
r
e
p
o
r
ted
g
o
o
d
r
es
u
lts
f
o
r
p
lan
t
d
is
ea
s
e
d
etec
tio
n
.
Pad
m
a
et
a
l.
[
1
7
]
f
o
cu
s
ed
o
n
Do
wn
e
y
an
d
Po
wd
er
y
Mild
ew,
wh
ic
h
p
r
o
d
u
ce
s
ig
n
if
ican
t
g
r
a
p
e
f
r
u
it
p
r
o
d
u
ctio
n
lo
s
s
es,
to
ef
f
ec
tiv
ely
d
etec
t
an
d
class
if
y
illn
ess
es
in
f
o
lio
d
escr
ip
tio
n
s
.
Fo
r
class
if
ier
-
b
ased
id
en
tific
atio
n
,
th
e
r
esear
ch
r
ec
o
m
m
en
d
ed
d
eletin
g
leaf
tr
aits
lik
e
th
e
m
ajo
r
an
d
s
m
all
ax
es.
E
ar
ly
illn
ess
d
etec
tio
n
an
d
ca
teg
o
r
izatio
n
b
en
ef
it
f
r
o
m
im
a
g
e
p
r
o
ce
s
s
in
g
.
E
lf
atim
i
et
a
l.
[
1
8
]
in
tr
o
d
u
ce
d
a
m
eth
o
d
f
o
r
class
if
y
in
g
b
ea
n
leaf
d
is
ea
s
es,
o
p
tim
izin
g
n
etwo
r
k
ar
ch
itec
tu
r
e,
h
y
p
er
p
ar
am
eter
s
,
a
n
d
ev
alu
atin
g
o
n
a
p
u
b
lic
d
at
aset.
Mo
b
ileNetV2
ar
ch
itectu
r
e
d
em
o
n
s
tr
ated
h
ig
h
ac
cu
r
ac
y
o
n
th
e
tr
ain
in
g
s
et
an
d
test
s
et
f
o
r
u
n
h
ea
lth
y
(
an
g
u
lar
leaf
s
p
o
t
d
is
ea
s
e
an
d
b
ea
n
r
u
s
t d
is
ea
s
e)
an
d
h
ea
lth
y
class
es.
Dep
th
-
wis
e
,
p
o
in
t
-
wis
e
co
n
v
o
lu
tio
n
s
wer
e
ad
d
ed
to
th
e
I
n
ce
p
tio
n
m
o
d
u
le
v
er
s
io
n
in
[1
9
]
.
T
h
e
I
n
ce
p
tio
n
m
o
d
u
le
an
d
p
r
e
-
tr
ai
n
ed
Mo
b
ileNet
wer
e
th
e
s
u
p
p
o
r
t e
x
tr
ac
to
r
s
f
o
r
h
ig
h
-
q
u
ality
p
ictu
r
e
f
ea
tu
r
es.
Fo
r
cr
o
p
d
is
ea
s
e
class
if
icatio
n
an
d
d
etec
tio
n
,
a
f
u
lly
c
o
n
n
ec
te
d
So
f
tm
ax
lay
er
an
d
s
in
g
le
s
h
o
t
d
etec
to
r
(
SSD
)
b
lo
ck
wer
e
in
clu
d
ed
.
T
h
e
m
o
d
el
was
tr
ain
ed
u
s
in
g
two
-
s
tag
e
tr
an
s
f
er
lear
n
in
g
.
W
u
et
a
l
.
[
2
0
]
in
tr
o
d
u
ce
d
a
f
in
e
-
g
r
ain
e
d
d
is
ea
s
e
ca
teg
o
r
izatio
n
m
eth
o
d
u
s
in
g
an
a
tten
tio
n
n
etwo
r
k
.
T
h
e
"Cl
ass
if
icatio
n
m
o
d
el"
in
co
r
p
o
r
ated
atten
tio
n
m
ec
h
an
is
m
s
f
o
r
en
h
an
ce
d
id
en
tific
atio
n
.
Du
r
in
g
tr
ain
in
g
,
a
"Reco
n
s
tr
u
ctio
n
-
g
e
n
er
atio
n
m
o
d
el
"
d
ir
ec
ted
f
o
cu
s
o
n
d
if
f
er
en
tiatin
g
ar
ea
s
,
an
d
ad
v
er
s
ar
ial
lo
s
s
r
ed
u
ce
d
n
o
is
e
f
r
o
m
t
h
e
"Discr
im
in
atio
n
m
o
d
el"
.
T
h
ese
wer
e
u
s
ed
ex
clu
s
iv
ely
d
u
r
in
g
tr
ain
in
g
,
a
v
o
id
in
g
co
m
p
lex
ity
i
n
th
e
in
f
er
en
ce
p
h
ase.
T
h
e
m
eth
o
d
im
p
r
o
v
ed
g
e
n
er
aliza
tio
n
ab
ilit
y
,
in
cr
ea
s
in
g
id
en
tific
atio
n
ac
cu
r
ac
y
with
lo
wer
m
e
m
o
r
y
r
eq
u
ir
em
en
ts
.
[
2
1
]
ex
tr
ac
ted
d
ee
p
co
r
n
p
lan
t
ch
ar
ac
ter
is
tics
u
s
in
g
two
p
r
e
-
tr
ain
ed
C
NNs,
E
f
f
icien
tNetB
0
,
an
d
Den
s
eNe
t1
2
1
.
Dee
p
f
ea
tu
r
es
f
r
o
m
ea
ch
C
NN
wer
e
co
n
ca
ten
ated
to
cr
ea
te
a
m
o
r
e
co
m
p
licated
f
ea
tu
r
e
s
et
to
im
p
r
o
v
e
m
o
d
el
lear
n
in
g
.
Dat
a
au
g
m
en
tatio
n
d
iv
e
r
s
if
ied
th
e
tr
ain
in
g
d
ataset
to
h
elp
th
e
m
o
d
el
h
an
d
le
m
o
r
e
co
m
p
licated
in
s
tan
ce
s
.
Ah
m
ad
et
a
l.
[
2
2
]
u
s
ed
m
em
o
r
y
-
ef
f
icien
t
C
NN
s
to
id
en
tif
y
p
lan
t
d
is
ea
s
e
s
y
m
p
to
m
s
.
T
h
e
s
u
g
g
ested
tr
ain
in
g
s
etu
p
r
e
d
u
ce
d
tr
ai
n
in
g
tim
e
an
d
h
a
n
d
led
class
im
b
alan
ce
u
s
in
g
s
tatis
tics
.
S
tep
wi
s
e
tr
an
s
f
er
lear
n
in
g
was
s
u
g
g
ested
to
ad
d
r
ess
n
eg
ativ
e
tr
an
s
f
er
lear
n
in
g
c
o
n
ce
r
n
s
d
u
r
i
n
g
k
n
o
wled
g
e
tr
an
s
f
er
b
etwe
en
d
o
m
ai
n
s
.
C
h
en
et
a
l.
[
2
3
]
im
p
r
o
v
ed
Y
OL
Ov
5
f
o
r
r
ea
l
-
tim
e
s
tr
awb
er
r
y
d
is
ea
s
e
d
etec
tio
n
.
T
o
d
ec
r
e
ase
p
ar
am
eter
s
an
d
FLOPs,
it
in
clu
d
ed
Gh
o
s
tC
o
n
v
.
An
in
v
o
lu
tio
n
o
p
e
r
ato
r
b
r
o
ad
e
n
ed
t
h
e
r
ec
e
p
tiv
e
f
iel
d
,
wh
ile
a
C
B
AM
in
cr
ea
s
ed
f
ea
tu
r
e
ex
tr
ac
tio
n
.
C
o
n
ten
t
-
Awa
r
e
R
eAss
em
b
ly
o
f
Featu
r
es
r
e
p
lace
d
u
p
s
am
p
lin
g
.
A
m
o
d
if
ied
lig
h
tweig
h
t
C
NN
m
ay
en
h
an
ce
f
in
e
-
g
r
ai
n
ed
cr
o
p
d
is
ea
s
e
ca
teg
o
r
izatio
n
[
2
4
]
.
T
h
e
u
p
g
r
ad
ed
Sq
u
ee
ze
Nex
t
m
o
d
el
with
a
m
u
lti
-
s
ca
le
co
n
v
o
lu
tio
n
k
er
n
el
a
n
d
co
o
r
d
i
n
ate
atten
tio
n
m
ec
h
a
n
is
m
o
u
tp
er
f
o
r
m
ed
th
e
o
r
i
g
in
al
m
o
d
el
in
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
.
T
h
e
lo
wer
m
o
d
el
s
ize
an
d
s
o
m
ewh
at
g
r
ea
ter
ac
c
u
r
ac
y
o
f
R
esNet5
0
an
d
Mo
b
ileNetV2
co
m
p
ar
e
d
to
Xce
p
tio
n
.
A
r
ec
o
n
s
tr
u
cted
r
esid
u
al
d
en
s
e
n
etwo
r
k
f
o
r
t
o
m
ato
leaf
d
is
ea
s
e
d
etec
tio
n
[
2
5
]
co
m
b
in
e
d
d
ee
p
r
esid
u
al
an
d
d
en
s
e
n
etwo
r
k
b
en
ef
its
.
T
h
e
m
o
d
el,
o
r
ig
in
a
lly
b
u
ilt
f
o
r
p
ictu
r
e
s
u
p
er
-
r
eso
lu
tio
n
,
s
co
r
ed
9
5
%
o
n
th
e
T
o
m
ato
test
d
ataset.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
p
la
n
t
d
is
ea
s
e
p
r
ed
ictio
n
was
s
h
o
w
n
in
Fig
u
r
e
1
.
T
h
e
r
esear
ch
m
eth
o
d
o
lo
g
y
in
v
o
lv
ed
s
ev
er
al
s
eq
u
en
tial
s
tep
s
to
en
s
u
r
e
r
o
b
u
s
tn
ess
a
n
d
ef
f
ec
tiv
en
ess
in
p
lan
t
d
is
ea
s
e
clas
s
if
icatio
n
.
I
n
itially
,
a
d
iv
er
s
e
d
ataset
was
co
m
p
iled
,
co
n
s
is
tin
g
o
f
im
a
g
es
p
o
r
tr
ay
in
g
b
o
th
d
is
ea
s
ed
an
d
h
ea
lth
y
s
tates
ac
r
o
s
s
v
ar
io
u
s
p
lan
t
ty
p
es.
R
ig
o
r
o
u
s
ef
f
o
r
ts
wer
e
m
ad
e
to
en
s
u
r
e
s
u
f
f
icien
t
co
v
er
a
g
e
o
f
p
lan
t
d
is
ea
s
es
an
d
au
th
en
ticity
o
f
t
h
e
d
ataset
to
m
in
im
ize
b
iases
.
Fo
llo
win
g
d
ata
co
llectio
n
,
th
e
d
atase
t
was
m
eticu
lo
u
s
ly
p
r
ep
ar
e
d
b
y
d
iv
id
in
g
it
in
to
d
is
tin
ct
s
u
b
s
ets
co
r
r
esp
o
n
d
in
g
to
d
if
f
er
en
t
p
lan
t
ty
p
es
s
u
c
h
as
Ap
p
le,
C
h
er
r
y
,
C
o
r
n
,
Gr
ap
e,
Peac
h
,
Pep
p
e
r
b
ell,
Po
tato
,
Stra
wb
er
r
y
,
an
d
T
o
m
ato
.
T
h
e
n
e
x
t
p
h
ase
in
v
o
lv
ed
p
ar
titi
o
n
in
g
ea
ch
p
lan
t
-
s
p
ec
if
ic
d
ataset
s
u
b
s
et
in
to
tr
ain
i
n
g
,
an
d
test
in
g
s
u
b
s
ets
u
s
in
g
ap
p
r
o
p
r
iate
r
atio
s
.
Sp
ec
ial
atten
tio
n
was
g
iv
en
to
m
ain
tain
in
g
p
r
o
p
o
r
ti
o
n
al
r
ep
r
esen
tatio
n
o
f
d
is
ea
s
ed
an
d
h
ea
lth
y
s
am
p
les
in
ea
ch
s
u
b
s
et
to
av
o
id
b
ias
an
d
en
s
u
r
e
m
o
d
el
g
en
e
r
aliza
tio
n
.
Su
b
s
eq
u
en
tly
,
s
tan
d
alo
n
e
C
NN
m
o
d
els
wer
e
d
ev
elo
p
e
d
,
tailo
r
ed
s
p
ec
if
ically
f
o
r
p
la
n
t d
is
ea
s
e
class
if
icatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
2
1
-
1
7
3
0
1724
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
et
h
o
d
o
lo
g
y
T
h
e
C
NN
m
o
d
els
wer
e
f
in
e
-
tu
n
ed
o
n
th
e
tr
ain
in
g
s
et
o
f
ea
ch
p
lan
t
-
s
p
ec
if
ic
d
ataset
s
u
b
s
et,
with
ad
ju
s
tm
en
ts
m
ad
e
to
h
y
p
e
r
p
a
r
am
eter
s
an
d
r
eg
u
lar
izatio
n
t
ec
h
n
iq
u
es.
Mo
d
el
v
alid
atio
n
was
co
n
d
u
cted
o
n
co
r
r
esp
o
n
d
in
g
v
alid
atio
n
s
u
b
s
ets,
w
ith
p
er
f
o
r
m
an
ce
m
etr
i
cs
m
o
n
ito
r
ed
an
d
ar
ch
itectu
r
e
r
ef
in
ed
b
ased
o
n
r
esu
lts
.
I
n
p
ar
allel,
s
tan
d
alo
n
e
GC
N
m
o
d
els
wer
e
co
n
s
tr
u
cted
to
ex
p
lo
it
r
elatio
n
al
in
f
o
r
m
atio
n
en
co
d
ed
in
g
r
ap
h
s
tr
u
ctu
r
es
o
f
th
e
d
ataset
s
u
b
s
ets.
Gr
ap
h
r
ep
r
esen
tat
io
n
s
wer
e
co
n
s
tr
u
cted
wh
e
r
e
n
o
d
es
r
ep
r
esen
ted
p
lan
ts
an
d
ed
g
es r
ep
r
esen
ted
r
elatio
n
s
h
ip
s
s
u
ch
as c
o
-
o
cc
u
r
r
en
ce
o
r
s
p
atial
p
r
o
x
im
ity
.
As
a
last
p
h
ase
o
f
m
eth
o
d
o
lo
g
y
,
a
n
in
teg
r
ated
ar
c
h
itectu
r
e
co
m
b
in
in
g
C
NNs
an
d
GC
Ns
wa
s
d
ev
elo
p
e
d
to
f
u
s
e
v
is
u
al
an
d
r
elatio
n
al
in
f
o
r
m
atio
n
f
o
r
e
n
h
an
ce
d
class
if
icatio
n
.
T
h
is
in
v
o
lv
ed
estab
lis
h
in
g
co
n
n
ec
tio
n
s
b
etwe
en
C
NN
an
d
GC
N
co
m
p
o
n
en
ts
to
f
a
cilitate
s
ea
m
les
s
in
f
o
r
m
atio
n
f
lo
w
an
d
f
ea
tu
r
e
in
teg
r
atio
n
.
T
h
e
in
teg
r
ated
m
o
d
el
was
tr
ain
ed
o
n
th
e
tr
ain
in
g
s
ets
o
f
ea
ch
p
lan
t
-
s
p
ec
if
ic
d
ataset
s
u
b
s
et,
wi
th
p
ar
am
eter
s
f
in
e
-
tu
n
ed
an
d
f
u
s
io
n
s
tr
ateg
ies
o
p
tim
ized
to
m
ax
im
ize
p
er
f
o
r
m
an
ce
.
Mo
d
el
v
alid
atio
n
was
p
er
f
o
r
m
ed
o
n
co
r
r
esp
o
n
d
i
n
g
v
alid
atio
n
s
u
b
s
ets,
with
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
a
g
ain
s
t
s
tan
d
alo
n
e
C
NN
an
d
GC
N
m
o
d
els.
Af
ter
ap
p
ly
in
g
GC
N+
C
NN
h
y
b
r
d
in
teg
r
aio
n
,
it
is
o
b
s
er
v
ed
th
at
th
e
r
es
u
lts
with
in
teg
r
ated
m
o
d
el
was b
etter
th
an
th
e
in
d
i
v
id
u
al
m
o
d
els.
2
.
1
.
P
l
a
nt
lea
f
i
m
a
g
e
da
t
a
s
et
g
a
t
hering
a
nd
prepa
ra
t
io
n
A
p
lan
t le
af
im
ag
e
d
ataset
was
g
ath
er
ed
f
r
o
m
Kag
g
le
[
26
]
.
T
h
e
d
ataset
co
n
tain
s
3
1
class
es
o
f
im
ag
es
with
Ap
p
le,
C
o
r
n
,
Gr
a
p
e,
Pea
ch
,
Pep
p
er
b
ell,
Po
tato
,
Stra
w
b
er
r
y
,
an
d
T
o
m
ato
t
y
p
es
.
T
h
i
s
d
ataset
is
f
u
r
th
er
d
iv
id
ed
as
s
er
r
ate
d
atasets
.
T
h
e
d
etails
o
f
s
ep
a
r
ated
d
atasets
ar
e
s
h
o
wn
in
T
ab
le
1
.
Fro
m
T
ab
le
1
,
it
is
o
b
s
er
v
ed
th
at
th
e
n
u
m
b
er
s
am
p
les
av
ailab
le
f
r
o
m
Ap
p
le,
C
o
r
n
,
Gr
a
p
e,
Peac
h
,
Pep
p
er
b
ell,
Po
tato
,
T
o
m
ato
an
d
Stra
wb
er
r
y
d
atasets
ar
e
3
1
7
1
,
3
8
5
2
,
4
0
6
2
,
2
6
5
7
,
2
4
7
5
,
2
1
5
2
,
1
8
1
6
0
,
an
d
1
5
6
5
r
esp
ec
tiv
ely
.
2
.
2
.
Co
nv
o
lutio
na
l neura
l
net
wo
rk
s
C
NNs
ar
e
DL
m
o
d
els
f
o
r
i
m
ag
e
id
en
tific
atio
n
an
d
class
if
icatio
n
.
C
o
n
v
o
lu
tio
n
al,
p
o
o
l
in
g
,
an
d
f
u
lly
lin
k
ed
C
NN
lay
er
s
ca
p
tu
r
e
h
ier
ar
ch
ical
an
d
s
p
atial
p
ictu
r
e
ch
ar
ac
ter
is
tics
well.
C
N
Ns
ex
ce
l
at
p
lan
t
d
is
ea
s
e
ca
teg
o
r
izatio
n
.
C
NNs
ca
n
ass
ess
d
etailed
p
lan
t
leaf
p
atter
n
s
a
n
d
te
x
tu
r
es
to
id
en
t
if
y
h
ea
lth
y
f
r
o
m
u
n
h
ea
lth
y
p
lan
ts
b
y
au
to
m
ati
ca
lly
lear
n
in
g
k
ey
in
f
o
r
m
ati
o
n
f
r
o
m
p
h
o
to
s
.
C
NNs
clas
s
if
y
p
lan
t
d
is
ea
s
es
ac
cu
r
ately
an
d
e
f
f
icien
tly
u
s
i
n
g
f
ea
tu
r
e
e
x
tr
ac
tio
n
an
d
h
ie
r
ar
ch
ical
r
ep
r
esen
tatio
n
lea
r
n
i
n
g
.
C
NNs
h
av
e
im
p
r
o
v
e
d
p
lan
t
d
is
ea
s
e
ca
teg
o
r
izatio
n
ac
cu
r
ac
y
an
d
s
p
ee
d
,
e
n
ab
lin
g
m
o
r
e
p
r
o
m
p
t
an
d
ef
f
e
ctiv
e
ag
r
icu
ltu
r
a
l
tr
ea
tm
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
la
n
t d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
n
o
ve
l in
teg
r
a
tio
n
o
f d
ee
p
lea
r
n
in
g
…
(
S
a
ka
Uma
Ma
h
esw
a
r
a
)
1725
T
ab
le
1
.
Data
s
et
p
r
ep
a
r
atio
n
d
etails
D
a
t
a
s
e
t
Ty
p
e
o
f
i
ma
g
e
s
N
u
mb
e
r
o
f
i
m
a
g
e
s
A
p
p
l
e
_
d
a
t
a
se
t
A
p
p
l
e
_
_
_
A
p
p
l
e
_
sc
a
b
6
3
0
A
p
p
l
e
_
_
_
B
l
a
c
k
_
r
o
t
6
2
1
A
p
p
l
e
_
_
_
C
e
d
a
r
_
a
p
p
l
e
_
r
u
s
t
2
7
5
A
p
p
l
e
_
_
_
h
e
a
l
t
h
y
1
6
4
5
C
o
r
n
_
d
a
t
a
s
e
t
C
o
r
n
_
C
e
r
c
o
s
p
o
r
a
_
l
e
a
f
_
s
p
o
t
5
1
3
C
o
r
n
_
C
o
mm
o
n
_
r
u
s
t
_
1
1
9
2
C
o
r
n
_
h
e
a
l
t
h
y
1
1
6
2
C
o
r
n
_
N
o
r
t
h
e
r
n
_
Le
a
f
_
B
l
i
g
h
t
9
8
5
G
r
a
p
e
_
d
a
t
a
se
t
G
r
a
p
e
_
B
l
a
c
k
_
r
o
t
1
1
8
0
G
r
a
p
e
_
Es
c
a
_
(
B
l
a
c
k
_
M
e
a
s
l
e
s)
1
3
8
3
G
r
a
p
e
_
h
e
a
l
t
h
y
4
2
3
G
r
a
p
e
_
Le
a
f
_
b
l
i
g
h
t
1
0
7
6
P
e
a
c
h
_
d
a
t
a
s
e
t
P
e
a
c
h
_
_
_
B
a
c
t
e
r
i
a
l
_
s
p
o
t
2
2
9
7
P
e
a
c
h
_
_
_
h
e
a
l
t
h
y
3
6
0
P
e
p
p
e
r
b
e
l
l
_
d
a
t
a
set
P
e
p
p
e
b
e
l
l
_
B
a
c
t
e
r
i
a
l
_
s
p
o
t
9
9
7
P
e
p
p
e
r
b
e
l
l
_
h
e
a
l
t
h
y
1
4
7
8
P
o
t
a
t
o
_
d
a
t
a
s
e
t
P
o
t
a
t
o
_
_
_
Ea
r
l
y
_
b
l
i
g
h
t
1
0
0
0
P
o
t
a
t
o
_
_
_
h
e
a
l
t
h
y
1
5
2
P
o
t
a
t
o
_
_
_
La
t
e
_
b
l
i
g
h
t
1
0
0
0
To
ma
t
o
_
d
a
t
a
s
e
t
To
ma
t
o
_
_
_
B
a
c
t
e
r
i
a
l
_
sp
o
t
2
1
2
7
To
ma
t
o
_
_
_
Ea
r
l
y
_
b
l
i
g
h
t
1
0
0
0
To
ma
t
o
_
_
_
La
t
e
_
b
l
i
g
h
t
1
9
0
9
To
ma
t
o
_
_
_
Le
a
f
_
M
o
l
d
9
5
2
To
ma
t
o
_
S
e
p
t
o
r
i
a
_
l
e
a
f
_
sp
o
t
1
7
7
1
To
ma
t
o
_
S
p
i
d
e
r
_
m
i
t
e
s
Tw
o
-
sp
o
t
t
e
d
_
s
p
i
d
e
r
_
mi
t
e
1
6
7
6
To
ma
t
o
_
_
_
Ta
r
g
e
t
_
S
p
o
t
1
4
0
4
To
ma
t
o
_
_
m
o
sa
i
c
_
v
i
r
u
s
3
7
3
To
ma
t
o
_
Y
e
l
l
o
w
_
Le
a
f
_
C
u
r
l
_
V
i
r
u
s
5
3
5
7
To
ma
t
o
_
_
_
h
e
a
l
t
h
y
1
5
9
1
S
t
r
a
w
b
e
r
r
y
_
d
a
t
a
s
e
t
S
t
r
a
w
b
e
r
r
y
_
_
_
Le
a
f
_
s
c
o
r
c
h
1
1
0
9
S
t
r
a
w
b
e
r
r
y
_
_
_
h
e
a
l
t
h
y
4
5
6
2
.
3
.
G
ra
ph
co
nv
o
lutio
na
l ne
t
wo
rk
s
GC
Ns
ar
e
g
o
o
d
at
ca
p
tu
r
in
g
lin
k
ag
es
a
n
d
d
ep
e
n
d
en
cies
in
n
o
n
-
E
u
clid
ea
n
d
o
m
ain
s
i
n
clu
d
in
g
s
o
cial,
citatio
n
,
an
d
b
io
l
o
g
ica
l
n
etwo
r
k
s
,
u
n
lik
e
g
r
id
-
lik
e
n
eu
r
al
n
etwo
r
k
s
.
GC
Ns
ca
n
b
e
u
s
ed
to
class
if
y
p
lan
t
d
is
ea
s
es
b
y
ev
alu
atin
g
co
r
r
elatio
n
s
b
etwe
en
p
lan
t
s
p
ec
ies,
wea
th
er
,
a
n
d
g
eo
g
r
ap
h
y
.
b
y
p
r
o
p
ag
atin
g
in
f
o
r
m
atio
n
ac
r
o
s
s
th
e
n
etwo
r
k
v
ia
g
r
ap
h
co
n
v
o
lu
tio
n
al
la
y
er
s
,
GC
Ns
let
th
e
m
o
d
el
to
lear
n
f
r
o
m
d
ata
p
o
in
t
in
ter
co
n
n
ec
tiv
ity
.
I
n
p
la
n
t
d
is
ea
s
e
ca
teg
o
r
izatio
n
,
GC
Ns
m
ay
ca
p
tu
r
e
in
tr
icate
co
n
n
ec
tio
n
s
b
etwe
en
p
lan
ts
,
illn
ess
es,
an
d
ex
ter
n
al
v
ar
iab
les,
h
elp
in
g
to
c
o
m
p
r
e
h
en
d
th
e
a
g
r
icu
ltu
r
al
en
v
ir
o
n
m
en
t.
I
n
c
o
r
p
o
r
atin
g
r
elatio
n
al
in
f
o
r
m
atio
n
in
to
p
lan
t
d
is
ea
s
e
class
if
icatio
n
u
s
in
g
GC
Ns
o
f
f
er
s
a
p
o
s
s
ib
le
p
ath
f
o
r
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
an
d
co
n
tex
t
-
a
war
e
d
is
ea
s
e
d
etec
tio
n
in
ag
r
ic
u
ltu
r
e.
2
.
4
.
I
nte
g
ra
t
io
n o
f
CNN
a
nd
G
CN
T
h
e
co
m
b
in
atio
n
o
f
GC
Ns
with
C
NN
s
f
o
r
p
lan
t
d
is
ea
s
e
ca
teg
o
r
izatio
n
is
in
n
o
v
a
tiv
e
an
d
s
y
n
er
g
is
tic.
T
h
is
h
y
b
r
id
m
o
d
el
co
m
b
in
es
C
NNs
'
v
is
u
al
p
atter
n
r
ec
o
g
n
itio
n
with
G
C
Ns
'
ca
p
ac
ity
to
r
ep
r
esen
t
ag
r
icu
ltu
r
al
n
etwo
r
k
in
ter
ac
tio
n
s
.
T
h
e
co
m
b
in
ed
GC
N+
C
NN
m
o
d
el
p
r
o
v
id
es
a
m
o
r
e
co
m
p
let
e
an
d
co
n
tex
t
-
awa
r
e
p
lan
t
d
is
ea
s
e
d
iag
n
o
s
is
s
o
lu
tio
n
b
y
co
m
b
in
in
g
s
p
atial
im
ag
e
ch
ar
ac
ter
is
tics
with
g
r
ap
h
-
b
a
s
e
d
i
n
f
o
r
m
a
t
i
o
n
s
u
c
h
p
l
a
n
t
s
p
e
c
i
e
s
r
e
la
t
i
o
n
s
h
i
p
s
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
p
a
r
a
m
e
t
e
r
s
.
T
h
is
n
o
v
e
l
m
e
t
h
o
d
i
m
p
r
o
v
e
s
a
c
c
u
r
a
c
y
a
n
d
i
n
t
e
r
p
r
et
a
b
i
l
it
y
,
o
f
f
e
r
i
n
g
a
c
o
m
p
r
e
h
e
n
s
i
v
e
f
o
u
n
d
a
t
i
o
n
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
d
i
s
e
as
e
c
o
n
t
r
o
l
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Du
r
in
g
t
h
e
d
ata
p
r
ep
ar
atio
n
s
t
ag
e,
eig
h
t
d
atasets
wer
e
cr
ea
te
d
,
ea
ch
tailo
r
ed
f
o
r
ex
p
er
im
e
n
tatio
n
.
All
ex
p
er
im
en
ts
wer
e
ca
r
r
ied
o
u
t
in
Go
o
g
le
C
o
lab
u
s
in
g
Py
T
o
r
ch
.
I
n
itially
,
a
C
NN
s
er
v
ed
as
th
e
b
ase
m
o
d
el.
Su
b
s
eq
u
en
tly
,
GC
N
was
im
p
l
em
en
ted
i
n
d
iv
id
u
ally
with
ea
c
h
o
f
th
e
eig
h
t
d
atasets
.
Fin
ally
,
a
n
o
v
el
in
teg
r
ated
ap
p
r
o
ac
h
,
co
m
b
in
in
g
b
o
th
C
NN
an
d
GC
N
(
C
NN+
GC
N)
,
was a
p
p
lied
f
o
r
a
co
m
p
r
eh
e
n
s
iv
e
ev
alu
atio
n
.
3
.
1
.
Appl
y
ing
co
nv
o
lutio
na
l
neura
l net
wo
rk
s
I
n
th
e
e
x
p
er
im
e
n
tatio
n
p
h
ase
,
we
em
p
lo
y
ed
a
C
NN
as
th
e
f
o
u
n
d
atio
n
al
m
o
d
el
f
o
r
p
la
n
t
d
is
ea
s
e
class
if
icatio
n
.
All
th
e
eig
h
t
d
atasets
u
n
d
er
wen
t
p
r
e
p
r
o
c
ess
in
g
an
d
o
r
g
an
izatio
n
,
u
til
izin
g
th
e
Py
T
o
r
ch
f
r
am
ewo
r
k
with
in
G
o
o
g
le
C
o
lab
f
o
r
f
lex
i
b
ilit
y
an
d
s
ca
lab
il
ity
.
I
m
ag
e
r
esizin
g
to
a
c
o
n
s
i
s
ten
t
d
im
en
s
io
n
o
f
224
×
2
2
4
p
ix
els
an
d
c
o
n
v
er
s
io
n
to
ten
s
o
r
s
wer
e
ac
h
iev
ed
t
h
r
o
u
g
h
Py
T
o
r
c
h
'
s
to
r
ch
v
is
io
n
l
ib
r
ar
y
.
T
h
e
d
ataset
was
th
en
s
p
lit
in
to
tr
ain
i
n
g
a
n
d
test
in
g
s
ets
to
en
s
u
r
e
r
o
b
u
s
t
m
o
d
el
e
v
alu
atio
n
.
T
h
e
C
NN
m
o
d
el
ar
c
h
itectu
r
e,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
2
1
-
1
7
3
0
1726
d
esig
n
ed
to
ca
p
tu
r
e
s
p
atial
f
ea
tu
r
es with
in
th
e
im
ag
es,
co
m
p
r
is
ed
co
n
v
o
lu
tio
n
al
lay
er
s
f
o
r
h
ier
ar
ch
ical
p
atter
n
ex
tr
ac
tio
n
,
f
o
llo
wed
b
y
m
a
x
-
p
o
o
lin
g
lay
er
s
f
o
r
d
o
wn
s
am
p
lin
g
.
T
h
e
f
u
lly
co
n
n
ec
ted
la
y
er
f
ac
ilit
ated
th
e
class
if
icatio
n
p
r
o
ce
s
s
f
o
r
f
o
u
r
d
is
ea
s
e
ca
teg
o
r
ies.
T
h
e
m
o
d
el
u
n
d
er
we
n
t
ten
ep
o
c
h
s
o
f
tr
ain
in
g
u
s
in
g
t
h
e
Ad
am
o
p
tim
izer
a
n
d
c
r
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
.
T
h
e
p
er
f
o
r
m
an
ce
was
ev
alu
ated
o
n
a
s
ep
ar
ate
test
s
et
to
ass
es
s
g
en
er
aliza
tio
n
ca
p
ab
ilit
ies.
T
h
e
r
esu
lts
o
f
C
N
N
ex
p
er
im
en
t
wer
e
s
h
o
wn
in
T
ab
le
2
.
T
ab
le
2
s
h
o
ws
ac
cu
r
ac
y
an
d
lo
s
s
v
alu
es
o
b
ta
in
ed
with
eig
h
t
ty
p
es
o
f
p
la
n
ts
.
T
h
e
ep
o
ch
wis
e
ac
cu
r
ac
y
a
n
d
lo
s
s
also
s
h
o
wn
f
o
r
two
d
atasets
n
am
ely
A
p
p
le
an
d
T
o
m
ato
.
Fig
u
r
e
2
s
h
o
ws
ep
o
ch
wis
e
p
er
f
o
r
m
a
n
ce
o
f
m
o
d
el
with
ap
p
le
d
ataset.
Fig
u
r
e
2
(
a)
s
h
o
ws
e
p
o
ch
wis
e
tr
ain
in
g
an
d
test
in
g
lo
s
s
f
o
r
A
p
p
le
d
ataset.
Fig
u
r
e
2
(
b
)
s
h
o
ws
ep
o
ch
wis
e
tr
ain
in
g
a
n
d
te
s
tin
g
ac
cu
r
ac
y
.
T
h
e
ac
cu
r
ac
y
o
b
tain
ed
f
o
r
Ap
p
le
d
ataset
is
8
8
%.
Fig
u
r
e
3
s
h
o
w
s
ep
o
ch
wis
e
p
er
f
o
r
m
an
ce
o
f
m
o
d
el
with
T
o
m
ato
d
ataset
.
Fig
u
r
e
3
(
a)
s
h
o
ws
ep
o
ch
wis
e
tr
ain
in
g
an
d
test
in
g
lo
s
s
.
Fig
u
r
e
3
(
b
)
s
h
o
ws
tr
ain
in
g
g
a
n
d
test
in
g
ac
cu
r
ac
y
f
o
r
T
o
m
ato
d
ataset.
T
h
e
ac
cu
r
ac
y
o
b
tain
e
d
f
o
r
Ap
p
le
d
ataset
is
8
8
%.
T
ab
le
2
.
R
esu
lts
with
C
NN
D
a
t
a
s
e
t
n
a
me
A
c
c
u
r
a
c
y
Lo
ss
A
p
p
l
e
_
d
a
t
a
se
t
0
.
9
3
0
.
1
8
C
o
r
n
_
d
a
t
a
s
e
t
0
.
9
3
0
.
1
5
G
r
a
p
e
_
d
a
t
a
se
t
0
.
9
2
0
.
2
0
P
e
a
c
h
_
d
a
t
a
s
e
t
0
.
9
7
0
.
0
5
P
e
p
p
e
r
b
e
l
l
_
d
a
t
a
set
0
.
9
5
0
.
1
1
P
o
t
a
t
o
_
d
a
t
a
s
e
t
0
.
9
7
0
.
0
7
To
ma
t
o
_
d
a
t
a
s
e
t
0
.
8
8
0
.
4
1
6
S
t
r
a
w
b
e
r
r
y
_
d
a
t
a
s
e
t
0
.
9
7
0
.
0
9
(
a)
(
b
)
Fig
u
r
e
2
.
E
p
co
h
wis
e
(
a
)
l
o
s
s
f
o
r
ap
p
le
d
ataset
an
d
(
b
)
ac
cu
r
a
cy
f
o
r
ap
p
le
d
ataset
(a
)
(b
)
Fig
u
r
e
3
.
E
p
co
h
wis
e
(
a
)
l
o
s
s
an
d
(
b
)
ac
cu
r
ac
y
f
o
r
to
m
ato
d
at
aset
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
la
n
t d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
n
o
ve
l in
teg
r
a
tio
n
o
f d
ee
p
lea
r
n
in
g
…
(
S
a
ka
Uma
Ma
h
esw
a
r
a
)
1727
3
.
2
.
Appl
y
ing
g
ra
ph
co
nv
o
l
utio
na
l net
wo
rk
T
h
e
GC
N
m
o
d
el
ar
ch
itectu
r
e
d
ef
in
es
th
e
s
tr
u
ctu
r
e
o
f
th
e
G
C
N
,
co
n
s
is
tin
g
o
f
two
f
u
lly
c
o
n
n
ec
te
d
lay
er
s
with
R
eL
U.
T
h
ese
lay
er
s
en
ab
le
th
e
m
o
d
el
to
ca
p
tu
r
e
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
b
e
twee
n
n
o
d
es
in
th
e
g
r
ap
h
.
Du
r
in
g
th
e
tr
ai
n
in
g
p
r
o
ce
d
u
r
e
,
th
e
lo
s
s
f
u
n
ctio
n
(
c
r
i
ter
io
n
)
is
s
p
ec
if
ied
as
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
,
an
d
t
h
e
o
p
tim
izer
(
o
p
tim
izer
)
is
d
ef
in
e
d
as Ad
am
.
T
h
e
ca
lcu
late_
ac
cu
r
ac
y
(
)
f
u
n
ctio
n
co
m
p
u
tes th
e
ac
cu
r
ac
y
o
f
m
o
d
el
p
r
ed
ictio
n
s
,
an
d
th
e
tr
ain
_
m
o
d
el(
)
f
u
n
ctio
n
tr
ain
s
th
e
GC
N
m
o
d
el
iter
ativ
ely
ac
r
o
s
s
ep
o
ch
s
,
ex
ec
u
tin
g
f
o
r
war
d
an
d
b
ac
k
war
d
p
ass
es
an
d
u
p
d
atin
g
m
o
d
el
p
ar
a
m
eter
s
b
ased
o
n
g
r
ad
ie
n
ts
.
Fo
llo
win
g
tr
ain
in
g
,
ev
alu
atio
n
,
a
n
d
p
er
f
o
r
m
an
ce
an
aly
s
is
ar
e
co
n
d
u
cted
.
T
h
e
m
o
d
el'
s
p
er
f
o
r
m
a
n
ce
is
ass
es
s
ed
u
s
in
g
th
e
test
d
ataset,
co
m
p
u
tin
g
m
etr
ics s
u
ch
as a
cc
u
r
ac
y
a
n
d
lo
s
s
.
T
h
e
r
esu
lts
o
f
GC
N
ex
p
er
im
en
t w
er
e
s
h
o
wn
in
T
ab
le
3
.
T
ab
le
3
s
h
o
ws ac
cu
r
ac
y
an
d
l
o
s
s
o
b
tain
ed
with
eig
h
t t
y
p
es
p
lan
ts
.
T
ab
le
3
.
R
esu
lts
with
GC
N
D
a
t
a
s
e
t
n
a
me
A
c
c
u
r
a
c
y
Lo
ss
A
p
p
l
e
_
d
a
t
a
se
t
0
.
9
4
0
.
2
4
C
o
r
n
_
d
a
t
a
s
e
t
0
.
9
3
0
.
3
4
G
r
a
p
e
_
d
a
t
a
se
t
0
.
9
3
0
.
1
7
P
e
a
c
h
_
d
a
t
a
s
e
t
0
.
9
7
0
.
0
9
P
e
p
p
e
r
b
e
l
l
_
d
a
t
a
set
0
.
9
6
0
.
2
1
P
o
t
a
t
o
_
d
a
t
a
s
e
t
0
.
9
5
0
.
0
9
To
ma
t
o
_
d
a
t
a
s
e
t
0
.
8
9
0
.
5
2
S
t
r
a
w
b
e
r
r
y
_
d
a
t
a
s
e
t
0
.
9
8
0
.
1
2
3
.
3
.
Appl
y
ing
no
v
el
inte
g
ra
t
io
n o
f
CNN
a
nd
G
CN
I
n
th
is
p
h
ase,
we
in
teg
r
ated
C
o
n
v
n
ets
with
GC
Ns
f
o
r
p
lan
t
d
is
ea
s
e
clas
s
if
icatio
n
,
aim
in
g
to
en
h
an
ce
ac
cu
r
ac
y
an
d
ef
f
icac
y
i
n
d
ia
g
n
o
s
in
g
d
is
ea
s
es
b
ased
o
n
le
af
im
ag
es.
Ou
r
ap
p
r
o
ac
h
ce
n
ter
s
o
n
th
e
r
o
b
u
s
t
R
esNet1
8
ar
ch
itectu
r
e
with
in
th
e
C
NN
co
m
p
o
n
en
t,
r
en
o
w
n
ed
f
o
r
its
ef
f
ec
tiv
en
ess
in
im
ag
e
class
if
icatio
n
task
s
.
B
y
ad
ap
tin
g
th
e
f
u
lly
co
n
n
ec
ted
la
y
er
to
o
u
r
d
atase
t's
r
eq
u
ir
em
en
ts
,
we
e
n
s
u
r
e
s
ea
m
less
in
teg
r
atio
n
with
th
e
s
u
b
s
eq
u
en
t stag
es o
f
o
u
r
h
y
b
r
id
m
o
d
el.
C
o
m
p
lem
e
n
tin
g
th
is
,
th
e
GC
N
co
m
p
o
n
en
t c
ap
tu
r
es r
elatio
n
al
in
f
o
r
m
atio
n
am
o
n
g
im
ag
es
th
r
o
u
g
h
two
ca
r
e
f
u
lly
c
r
af
ted
GC
N
lay
er
s
,
lev
er
a
g
in
g
g
r
ap
h
-
b
ased
r
ep
r
esen
tatio
n
s
.
Gr
ap
h
co
n
v
o
l
u
tio
n
al
o
p
e
r
atio
n
s
an
d
ac
tiv
at
io
n
f
u
n
cti
o
n
s
en
h
an
ce
th
e
cla
s
s
if
icatio
n
p
r
o
ce
s
s
with
n
u
an
ce
d
r
elatio
n
al
in
s
ig
h
ts
.
Du
r
in
g
tr
ai
n
in
g
,
o
u
r
h
y
b
r
i
d
m
o
d
el
u
n
d
er
g
o
es
o
p
tim
izatio
n
f
ac
ilit
ated
b
y
th
e
Ad
am
o
p
tim
izer
,
e
v
o
lv
in
g
c
o
llab
o
r
ativ
ely
t
o
e
n
h
an
ce
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
e
m
o
d
e
l
tr
av
er
s
es
ep
o
ch
s
with
a
s
h
ar
ed
lear
n
in
g
r
ate,
r
ef
in
in
g
p
ar
a
m
eter
s
th
r
o
u
g
h
iter
ativ
e
f
o
r
war
d
a
n
d
b
ac
k
war
d
p
ass
es.
T
h
e
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
g
u
id
es
o
p
tim
izatio
n
,
e
n
s
u
r
in
g
alig
n
m
en
t
with
g
r
o
u
n
d
tr
u
t
h
lab
e
ls
in
p
lan
t
d
is
ea
s
e
class
if
icatio
n
.
Po
s
t
-
tr
ain
in
g
,
r
ig
o
r
o
u
s
ev
alu
atio
n
o
n
a
n
in
d
ep
e
n
d
en
t
test
s
et
illu
m
in
ates
r
ea
l
-
wo
r
ld
p
er
f
o
r
m
an
ce
u
s
in
g
m
etr
ics
s
u
ch
as
test
lo
s
s
an
d
ac
c
u
r
ac
y
.
T
h
e
ag
g
r
eg
atio
n
o
f
a
v
er
ag
e
test
m
etr
ics
p
r
o
v
id
es
a
co
m
p
r
eh
e
n
s
iv
e
s
n
ap
s
h
o
t
o
f
t
h
e
m
o
d
el'
s
d
iag
n
o
s
tic
ca
p
ab
ilit
ies.
I
n
ess
en
ce
,
o
u
r
f
u
s
io
n
o
f
C
NN
an
d
GC
N
m
ar
k
s
a
n
ew
er
a
i
n
p
lan
t
d
is
ea
s
e
class
if
icat
io
n
,
p
r
o
m
is
in
g
u
n
p
ar
alleled
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
B
y
co
m
b
in
in
g
im
ag
e
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
r
elatio
n
al
in
f
o
r
m
atio
n
m
o
d
elin
g
,
o
u
r
h
y
b
r
id
m
o
d
el
s
tan
d
s
p
o
is
ed
to
r
ev
o
lu
tio
n
ize
ag
r
icu
ltu
r
al
tech
n
o
lo
g
y
,
en
h
a
n
cin
g
cr
o
p
p
r
o
tectio
n
an
d
s
u
s
tain
ab
le
p
r
ac
tices.
T
h
e
r
esu
lts
with
in
teg
r
ated
C
NN
an
d
GC
N
is
s
h
o
wn
in
T
ab
le
4
.
Fro
m
T
ab
le
4
,
it
is
o
b
s
er
v
ed
th
at,
th
e
in
teg
r
atio
n
o
f
C
NN
an
f
GC
N
b
o
o
s
t th
e
ac
cu
r
ac
y
an
d
r
ed
ice
th
e
lo
s
s
v
alu
es f
o
r
all
ty
p
es
o
f
p
lan
ts
.
T
ab
le
4
.
R
esu
lts
with
in
teg
r
atio
n
o
f
C
NN+
GC
N
D
a
t
a
s
e
t
N
a
me
A
c
c
u
r
a
c
y
Lo
ss
A
p
p
l
e
_
d
a
t
a
se
t
0
.
9
9
0
.
0
4
C
o
r
n
_
d
a
t
a
s
e
t
0
.
9
4
0
.
1
5
G
r
a
p
e
_
d
a
t
a
se
t
0
.
9
8
0
.
0
3
P
e
a
c
h
_
d
a
t
a
s
e
t
0
.
9
9
0
.
0
1
P
e
p
p
e
r
b
e
l
l
_
d
a
t
a
set
0
.
9
9
0
.
0
5
P
o
t
a
t
o
_
d
a
t
a
s
e
t
0
.
9
9
0
.
0
0
8
To
ma
t
o
_
d
a
t
a
s
e
t
0
.
9
8
0
.
0
5
S
t
r
a
w
b
e
r
r
y
_
d
a
t
a
s
e
t
0
.
9
9
0
.
0
0
1
T
h
e
ep
o
ch
wis
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
f
o
r
ap
p
le
d
ataset
is
s
h
o
wn
in
F
ig
u
r
e
4
.
Fig
u
r
e
4
(
a
)
s
h
o
ws
ep
o
ch
wis
e
tr
ain
in
g
ac
cu
r
ac
y
an
d
F
ig
u
r
e
4
(
b
)
s
h
o
ws
ep
o
ch
wis
e
tr
ain
in
g
lo
s
s
.
I
t
is
o
b
s
er
v
ed
th
at
th
e
ac
cu
r
ac
y
in
cr
ea
s
ed
g
r
ad
u
ally
f
r
o
m
e
p
o
ch
1
to
ep
o
c
h
-
1
0
.
T
h
e
tr
ain
i
n
g
lo
s
s
v
alu
e
v
al
u
es
g
r
ad
u
al
ly
d
ec
r
ea
s
ed
f
r
o
m
ep
o
ch
-
1
to
ep
o
ch
-
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
2
1
-
1
7
3
0
1728
T
h
e
ep
o
ch
wis
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
f
o
r
g
r
a
p
e
d
ataset
was
s
h
o
wn
in
F
ig
u
r
e
5
.
T
h
e
e
p
o
ch
wis
e
tr
ain
in
g
ac
cu
r
ac
y
is
s
h
o
wn
in
F
ig
u
r
e
5
(
a
)
.
Fig
u
r
e
5
(
b
)
s
h
o
ws
ep
o
ch
wis
e
tr
ain
in
g
lo
s
s
f
o
r
g
r
ap
e
d
ataset
I
t
is
id
en
tifie
d
th
at
th
e
ac
cu
r
ac
y
in
cr
ea
s
ed
g
r
ad
u
ally
f
r
o
m
ep
o
ch
1
to
ep
o
ch
-
1
0
.
T
h
e
tr
ain
i
n
g
lo
s
s
v
alu
e
v
alu
es
g
r
ad
u
ally
d
ec
r
ea
s
ed
f
r
o
m
e
p
o
ch
-
1
to
e
p
o
ch
-
1
0
.
T
h
e
s
im
ilar
ty
p
e
o
f
t
r
en
d
ac
h
iev
ed
f
o
r
all
t
h
e
eig
h
t d
atasets
.
(
a)
(
b
)
Fig
u
r
e
4
.
E
p
o
ch
wis
e
(
a)
ac
c
u
r
ac
y
an
d
(
b
)
l
o
s
s
v
alu
es f
o
r
ap
p
le
d
ataset
(
a)
(
b
)
Fig
u
r
e
5
.
E
p
o
ch
wis
e
(
a)
ac
c
u
r
ac
y
an
d
(
b
)
l
o
s
s
v
alu
es f
o
r
g
r
a
p
e
d
ataset
3
.
4
.
Co
m
pa
riso
n wit
h e
x
is
t
ing
wo
rk
T
ab
le
5
s
h
o
ws
th
e
co
m
p
ar
is
o
n
o
f
p
r
o
p
o
s
ed
wo
r
k
with
p
r
e
v
io
u
s
wo
r
k
.
Ullah
et
a
l.
[
2
]
,
ap
p
lied
a
n
o
v
el
Dee
p
Plan
tNet
an
d
ac
h
ie
v
ed
an
ac
c
u
r
ac
y
o
f
9
8
%
.
An
a
n
d
h
i
an
d
Sath
iam
o
o
r
th
y
[
5
]
,
t
h
e
en
s
em
b
le
m
o
d
el
o
f
s
ev
er
al
DL
tech
n
iq
u
es
g
iv
en
h
ig
h
est
ac
cu
r
ac
y
o
f
9
1
%.
L
ak
s
h
m
an
ar
ao
et
a
l.
[
1
4
]
,
a
n
ac
cu
r
ac
y
o
f
9
5
%
ac
h
iev
ed
with
tr
an
s
f
er
lear
n
in
g
tech
n
i
q
u
es.
T
h
e
p
r
o
p
o
s
ed
in
teg
r
atio
n
o
f
C
NN
an
d
GC
N
ac
h
iv
ed
a
n
ac
c
u
r
ac
y
o
f
9
9
% a
n
d
o
u
tp
er
f
o
r
m
ed
th
e
co
n
v
en
tio
n
al
m
o
d
els.
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
with
ex
i
s
tin
g
wo
r
k
D
a
t
a
s
e
t
N
a
me
A
c
c
u
r
a
c
y
D
e
e
p
P
l
a
n
t
N
e
t
[
2
]
9
8
%
En
se
mb
l
e
m
o
d
e
l
[
5
]
9
1
%
Tr
a
n
sf
e
r
l
e
a
r
n
i
n
g
[
1
4
]
9
5
%
P
r
o
p
o
se
d
m
e
t
h
o
d
9
9
%
4.
CO
NCLU
SI
O
N
P
lan
t
d
is
ea
s
e
s
h
ad
p
o
s
ed
s
ig
n
if
ican
t
ch
allen
g
es
to
g
lo
b
al
ag
r
icu
ltu
r
e,
p
r
o
f
o
u
n
d
l
y
im
p
ac
tin
g
cr
o
p
y
ield
s
an
d
th
r
ea
ten
in
g
f
o
o
d
s
ec
u
r
ity
.
Acc
u
r
ate
an
d
tim
ely
d
e
tectio
n
o
f
th
ese
d
is
ea
s
es
h
ad
b
ee
n
p
ar
am
o
u
n
t
f
o
r
m
itig
atin
g
th
eir
ad
v
er
s
e
ef
f
ec
t
s
.
I
n
th
is
s
tu
d
y
,
we
p
r
o
p
o
s
ed
a
n
o
v
el
ap
p
r
o
ac
h
f
o
r
p
lan
t
d
is
ea
s
e
class
if
ica
tio
n
b
y
in
teg
r
atin
g
C
NN
an
d
GC
Ns.
Ou
r
m
o
d
el
aim
ed
to
en
h
an
ce
class
if
icatio
n
ac
cu
r
ac
y
b
y
lev
er
ag
in
g
b
o
t
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
la
n
t d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
n
o
ve
l in
teg
r
a
tio
n
o
f d
ee
p
lea
r
n
in
g
…
(
S
a
ka
Uma
Ma
h
esw
a
r
a
)
1729
v
is
u
al
f
ea
tu
r
es
ex
tr
ac
ted
b
y
C
NNs
an
d
r
elatio
n
al
in
f
o
r
m
a
tio
n
ca
p
tu
r
ed
b
y
GC
Ns.
U
s
in
g
a
Kag
g
le
d
ataset
co
n
tain
in
g
im
a
g
es o
f
d
is
ea
s
ed
an
d
h
ea
lth
y
p
lan
t le
av
es f
r
o
m
3
1
class
es,
in
clu
d
in
g
Ap
p
le,
C
o
r
n
,
Gr
a
p
e,
Peac
h
,
Pep
p
er
b
ell,
Po
tato
,
Stra
wb
er
r
y
,
an
d
T
o
m
at
o
,
we
p
ar
titi
o
n
e
d
th
e
d
ataset
in
to
s
ep
ar
ate
s
u
b
s
ets
f
o
r
ea
ch
p
lan
t
ty
p
e.
Stan
d
alo
n
e
C
NN
m
o
d
e
ls
wer
e
tr
ain
ed
o
n
im
ag
e
d
ata
f
r
o
m
ea
ch
p
lan
t
ty
p
e,
wh
il
e
s
tan
d
alo
n
e
GC
N
m
o
d
els
u
tili
ze
d
g
r
ap
h
-
s
tr
u
ct
u
r
ed
d
ata
r
ep
r
esen
tin
g
p
lan
t
r
elatio
n
s
h
ip
s
with
in
ea
ch
s
u
b
s
et.
Ou
r
p
r
o
p
o
s
ed
in
teg
r
ated
C
NN
-
GC
N
m
o
d
el
ca
p
italized
o
n
th
e
co
m
p
lem
en
tar
y
s
tr
en
g
th
s
o
f
C
NNs
an
d
GC
Ns
to
ac
h
iev
e
im
p
r
o
v
e
d
class
if
icatio
n
p
e
r
f
o
r
m
an
ce
.
T
h
r
o
u
g
h
r
ig
o
r
o
u
s
ex
p
er
im
en
tatio
n
an
d
c
o
m
p
ar
ativ
e
an
aly
s
is
,
we
ev
alu
ated
th
e
ef
f
ec
tiv
en
ess
o
f
o
u
r
in
teg
r
ated
C
NN
-
GC
N
ap
p
r
o
ac
h
alo
n
g
s
id
e
s
tan
d
alo
n
e
C
NN
an
d
G
C
N
m
o
d
els ac
r
o
s
s
all
p
lan
t ty
p
es.
RE
F
E
R
E
NC
E
S
[
1
]
W
.
B
.
D
e
mi
l
i
e
,
“
P
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
:
a
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
t
h
e
p
e
r
f
o
r
ma
n
c
e
s,
”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
1
1
,
n
o
.
1
,
2
0
2
4
.
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
3
-
0
0
8
6
3
-
9.
[
2
]
N
.
U
l
l
a
h
e
t
a
l
.
,
“
A
n
e
f
f
e
c
t
i
v
e
a
p
p
r
o
a
c
h
f
o
r
p
l
a
n
t
l
e
a
f
d
i
s
e
a
ses
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
a
n
o
v
e
l
D
e
e
p
P
l
a
n
t
N
e
t
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
Fro
n
t
i
e
rs
i
n
P
l
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s
.
2
0
2
3
.
1
2
1
2
7
4
7
.
[
3
]
M
.
H
.
S
a
a
d
a
n
d
A
.
E.
S
a
l
ma
n
,
“
A
p
l
a
n
t
d
i
s
e
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
o
n
e
-
s
h
o
t
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
w
i
t
h
f
i
e
l
d
i
m
a
g
e
s,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
2
0
2
3
.
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
3
-
1
7
8
3
0
-
4.
[
4
]
R
a
ma
n
j
o
t
e
t
a
l
.
,
“
P
l
a
n
t
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
:
a
sy
s
t
e
m
a
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
1
0
,
p
.
4
7
6
9
,
2
0
2
3
.
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
1
0
4
7
6
9
.
[
5
]
D
.
F
.
R
o
s
e
A
n
a
n
d
h
i
a
n
d
S
.
S
a
t
h
i
a
m
o
o
r
t
h
y
,
"
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
a
u
t
o
m
a
t
e
d
r
i
c
e
p
l
a
n
t
d
i
s
e
a
s
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
,
"
2
0
2
3
Fi
rs
t
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
E
l
e
c
t
ri
c
a
l
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
C
AE
EC
I
)
,
Ti
r
u
c
h
e
n
g
o
d
e
,
I
n
d
i
a
,
2
0
2
3
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
EEC
I
5
8
2
4
7
.
2
0
2
3
.
1
0
3
7
0
8
0
9
.
[
6
]
S
.
D
e
g
a
d
w
a
l
a
,
D
.
V
y
a
s,
S
.
P
a
n
e
sa
r
,
D
.
E
b
e
n
e
z
e
r
,
D
.
D
.
P
a
n
d
y
a
a
n
d
V
.
D
.
S
h
a
h
,
"
R
e
v
o
l
u
t
i
o
n
i
z
i
n
g
h
o
p
s
p
l
a
n
t
d
i
s
e
a
s
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
h
a
r
n
e
ss
i
n
g
t
h
e
p
o
w
e
r
o
f
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
"
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
u
st
a
i
n
a
b
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rks
a
n
d
A
p
p
l
i
c
a
t
i
o
n
(
I
C
S
C
N
A)
,
Th
e
n
i
,
I
n
d
i
a
,
2
0
2
3
,
p
p
.
1
7
0
6
-
1
7
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
N
A
5
8
4
8
9
.
2
0
2
3
.
1
0
3
7
0
6
9
2
.
[
7
]
M
.
B
e
l
m
i
r
,
W
.
D
i
f
a
l
l
a
h
a
n
d
A
.
G
h
a
z
l
i
,
"
P
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
"
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
e
c
i
si
o
n
A
i
d
S
c
i
e
n
c
e
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
(
D
AS
A)
,
2
0
2
3
,
p
p
.
5
3
6
-
5
4
0
,
d
o
i
:
1
0
.
1
1
0
9
/
D
A
S
A
5
9
6
2
4
.
2
0
2
3
.
1
0
2
8
6
6
7
2
.
[
8
]
C
.
M
a
d
h
u
r
y
a
a
n
d
E.
A
.
Ju
b
i
l
s
o
n
,
"
Y
R
2
S
:
e
f
f
i
c
i
e
n
t
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
f
o
r
d
e
t
e
c
t
i
n
g
a
n
d
c
l
a
ssi
f
y
i
n
g
p
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
s
,
"
i
n
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
3
7
9
0
-
3
8
0
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
4
3
4
5
0
.
[
9
]
D
.
S
.
J
o
se
p
h
,
P
.
M
.
P
a
w
a
r
a
n
d
K
.
C
h
a
k
r
a
d
e
o
,
"
R
e
a
l
-
t
i
m
e
p
l
a
n
t
d
i
se
a
se
d
a
t
a
set
d
e
v
e
l
o
p
me
n
t
a
n
d
d
e
t
e
c
t
i
o
n
o
f
p
l
a
n
t
d
i
se
a
se
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
"
i
n
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
1
2
,
p
p
.
1
6
3
1
0
-
1
6
3
3
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
5
8
3
3
3
.
[
1
0
]
F
.
A
d
n
a
n
,
M
.
J
.
A
w
a
n
,
A
.
M
a
h
m
o
u
d
,
H
.
N
o
b
a
n
e
e
,
A
.
Y
a
si
n
a
n
d
A
.
M
.
Za
i
n
,
"
Ef
f
i
c
i
e
n
t
N
e
t
B
3
-
a
d
a
p
t
i
v
e
a
u
g
m
e
n
t
e
d
d
e
e
p
l
e
a
r
n
i
n
g
(
A
A
D
L)
f
o
r
m
u
l
t
i
-
c
l
a
ss
p
l
a
n
t
d
i
sea
s
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
"
i
n
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
8
5
4
2
6
-
8
5
4
4
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
0
3
1
3
1
.
[
1
1
]
R.
S.
R.
S
i
n
g
h
a
n
d
R
.
K
.
S
a
n
o
d
i
y
a
,
"
Ze
r
o
-
s
h
o
t
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
p
l
a
n
t
l
e
a
f
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
"
i
n
I
EEE
A
c
c
e
s
s
,
v
o
l
.
1
1
,
p
p
.
1
4
3
8
6
1
-
1
4
3
8
8
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
4
3
7
5
9
.
[
1
2
]
R
.
R
a
s
h
i
d
,
W
.
A
sl
a
m,
R
.
A
z
i
z
a
n
d
G
.
A
l
d
e
h
i
m
,
"
A
n
e
a
r
l
y
a
n
d
smar
t
d
e
t
e
c
t
i
o
n
o
f
c
o
r
n
p
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
s
u
s
i
n
g
i
o
t
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
u
l
t
i
-
m
o
d
e
l
s
,
"
i
n
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
2
3
1
4
9
-
2
3
1
6
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
5
7
0
9
9
.
[
1
3
]
A
.
A
h
ma
d
,
A
.
E.
G
a
m
a
l
a
n
d
D
.
S
a
r
a
sw
a
t
,
"
T
o
w
a
r
d
g
e
n
e
r
a
l
i
z
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
p
l
a
n
t
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
n
d
e
r
c
o
n
t
r
o
l
l
e
d
a
n
d
f
i
e
l
d
c
o
n
d
i
t
i
o
n
s
,
"
i
n
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
9
0
4
2
-
9
0
5
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
4
0
1
0
0
.
[
1
4
]
A
.
La
k
s
h
ma
n
a
r
a
o
,
N
.
S
u
p
r
i
y
a
a
n
d
A
.
A
r
u
l
mu
r
u
g
a
n
,
"
P
l
a
n
t
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
"
2
0
2
2
S
e
c
o
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
E
l
e
c
t
ri
c
a
l
,
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
S
u
s
t
a
i
n
a
b
l
e
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
AE
C
T
)
,
B
h
i
l
a
i
,
I
n
d
i
a
,
2
0
2
2
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
EC
T5
4
8
7
5
.
2
0
2
2
.
9
8
0
7
9
5
6
.
[
1
5
]
A
.
S
.
A
n
sari
e
t
a
l
.
,
“
I
mp
r
o
v
e
d
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
a
n
d
i
ma
g
e
p
r
o
c
e
ssi
n
g
e
n
a
b
l
e
d
m
e
t
h
o
d
o
l
o
g
y
f
o
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
g
r
a
p
e
l
e
a
f
d
i
sea
se
,
”
J
o
u
rn
a
l
o
f
Fo
o
d
Q
u
a
l
i
t
y
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
6
,
2
0
2
2
.
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
9
5
0
2
4
7
5
.
[
1
6
]
N
.
S
a
me
e
r
a
,
B
.
A
.
R
a
m,
P
.
S
.
S
.
P
r
a
sa
d
a
n
d
A
.
La
k
s
h
ma
n
a
r
a
o
,
"
P
l
a
n
t
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
u
s
i
n
g
M
LP,
c
o
n
v
n
e
t
s
a
n
d
d
e
n
se
n
e
t
mo
d
e
l
s
,
"
2
0
2
4
Fo
u
r
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
El
e
c
t
ri
c
a
l
,
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
S
u
s
t
a
i
n
a
b
l
e
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
AE
C
T
)
,
B
h
i
l
a
i
,
I
n
d
i
a
,
2
0
2
4
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
EC
T
6
0
2
0
2
.
2
0
2
4
.
1
0
4
6
8
8
9
5
.
[
1
7
]
U
.
P
a
d
ma
,
S
.
J
a
g
a
d
i
s
h
,
a
n
d
M
.
K
.
S
i
n
g
h
,
“
R
e
c
o
g
n
i
t
i
o
n
o
f
p
l
a
n
t
’
s
l
e
a
f
i
n
f
e
c
t
i
o
n
b
y
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
a
p
p
r
o
a
c
h
,
”
Ma
t
e
r
i
a
l
s
T
o
d
a
y
:
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
5
1
,
p
p
.
9
1
4
–
9
1
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
a
t
p
r
.
2
0
2
1
.
0
6
.
2
9
7
.
[
1
8
]
E.
El
f
a
t
i
m
i
,
R
.
Er
y
i
g
i
t
a
n
d
L.
El
f
a
t
i
m
i
,
"
B
e
a
n
s
l
e
a
f
d
i
se
a
ses
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
m
o
b
i
l
e
n
e
t
m
o
d
e
l
s
,
"
i
n
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
9
4
7
1
-
9
4
8
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
2
.
3
1
4
2
8
1
7
.
[
1
9
]
J.
C
h
e
n
,
W
.
C
h
e
n
,
A
.
Z
e
b
,
S
.
Y
a
n
g
a
n
d
D
.
Zh
a
n
g
,
"
Li
g
h
t
w
e
i
g
h
t
i
n
c
e
p
t
i
o
n
n
e
t
w
o
r
k
s
f
o
r
t
h
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
o
f
r
i
c
e
p
l
a
n
t
d
i
s
e
a
se
s
,
"
i
n
I
EEE
S
e
n
s
o
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
2
,
n
o
.
1
4
,
p
p
.
1
4
6
2
8
-
1
4
6
3
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
2
.
3
1
8
2
3
0
4
.
[
2
0
]
Y
.
W
u
,
X
.
F
e
n
g
a
n
d
G
.
C
h
e
n
,
"
P
l
a
n
t
l
e
a
f
d
i
se
a
ses
f
i
n
e
-
g
r
a
i
n
e
d
c
a
t
e
g
o
r
i
z
a
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
"
i
n
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
4
1
0
8
7
-
4
1
0
9
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
6
7
5
1
3
.
[
2
1
]
H
.
A
mi
n
,
A
.
D
a
r
w
i
s
h
,
A
.
E
.
H
a
ssa
n
i
e
n
a
n
d
M
.
S
o
l
i
ma
n
,
"
E
n
d
-
to
-
e
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
c
o
r
n
l
e
a
f
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
"
i
n
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
3
1
1
0
3
-
3
1
1
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
5
9
6
7
8
.
[
2
2
]
M
.
A
h
ma
d
,
M
.
A
b
d
u
l
l
a
h
,
H
.
M
o
o
n
a
n
d
D
.
H
a
n
,
"
P
l
a
n
t
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
i
n
i
m
b
a
l
a
n
c
e
d
d
a
t
a
se
t
s
u
si
n
g
e
f
f
i
c
i
e
n
t
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
w
i
t
h
st
e
p
w
i
se
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
"
i
n
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
4
0
5
6
5
-
1
4
0
5
8
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
1
9
6
5
5
.
[
2
3
]
S
.
C
h
e
n
,
Y
.
Li
a
o
,
F
.
Li
n
a
n
d
B
.
H
u
a
n
g
,
"
A
n
i
mp
r
o
v
e
d
l
i
g
h
t
w
e
i
g
h
t
Y
O
LO
v
5
a
l
g
o
r
i
t
h
m
f
o
r
d
e
t
e
c
t
i
n
g
st
r
a
w
b
e
r
r
y
d
i
sea
s
e
s
,
"
i
n
I
EEE
Ac
c
e
ss,
v
o
l
.
1
1
,
p
p
.
5
4
0
8
0
-
5
4
0
9
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
2
3
0
9
.
[
2
4
]
Y
.
Li
u
,
G
.
G
a
o
a
n
d
Z
.
Z
h
a
n
g
,
"
C
r
o
p
d
i
s
e
a
s
e
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
m
o
d
i
f
i
e
d
l
i
g
h
t
-
w
e
i
g
h
t
C
N
N
w
i
t
h
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sm
,
"
i
n
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
1
2
0
6
6
-
1
1
2
0
7
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
1
6
2
8
5
.
[
2
5
]
C
.
Zh
o
u
,
S
.
Z
h
o
u
,
J.
X
i
n
g
a
n
d
J
.
S
o
n
g
,
"
T
o
m
a
t
o
l
e
a
f
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
y
r
e
s
t
r
u
c
t
u
r
e
d
d
e
e
p
r
e
s
i
d
u
a
l
d
e
n
se
n
e
t
w
o
r
k
,
"
i
n
I
EE
E
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
2
8
8
2
2
-
2
8
8
3
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
5
8
9
4
.
[
2
6
]
A
b
d
a
l
l
a
h
A
l
i
,
"
P
l
a
n
t
V
i
l
l
a
g
e
D
a
t
a
set
"
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m/
d
a
t
a
s
e
t
s
/
a
b
d
a
l
l
a
h
a
l
i
d
e
v
/
p
l
a
n
t
v
i
l
l
a
g
e
-
d
a
t
a
se
t
/
d
a
t
a
.
(
a
c
c
e
s
se
d
o
n
D
e
c
e
mb
e
r
2
8
,
2
0
2
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
2
1
-
1
7
3
0
1730
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
k
a
Um
a
M
a
h
e
sw
a
r
a
R
a
o
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
As
so
c
iate
P
r
o
fe
ss
o
r,
De
p
a
rtme
n
t
o
f
CS
E
,
S
h
ri
Vish
n
u
En
g
in
e
e
ri
n
g
Co
ll
e
g
e
f
o
r
Wo
m
e
n
(A),
Bh
ima
v
a
rm
,
A.P
,
In
d
ia.
He
re
c
e
iv
e
d
h
is
P
h
.
D
.
fro
m
An
d
h
ra
U
n
iv
e
rsit
y
i
n
B
ig
Da
ta
An
a
l
y
ti
c
s.
He
h
a
s
m
o
re
th
a
n
1
8
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
.
He
h
a
d
p
u
b
li
sh
e
d
p
a
p
e
rs
in
re
p
u
ted
n
a
ti
o
n
a
l
a
n
d
in
ter
n
a
ti
o
n
a
l
jo
u
r
n
a
ls
.
His
a
re
a
s
o
f
in
tere
st
in
c
lu
d
e
b
i
g
d
a
ta,
so
ftwa
re
e
n
g
i
n
e
e
rin
g
,
d
a
ta
m
in
i
n
g
,
M
L,
a
n
d
AI.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
k
a
.
m
a
h
i@g
m
a
il
.
c
o
m
.
Dr
.
K
e
shetti
S
r
e
e
k
a
la
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
a
n
As
sista
n
t
P
r
o
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
CS
E
a
t
M
a
h
a
tma
G
a
n
d
h
i
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Hy
d
e
ra
b
a
d
,
I
n
d
ia.
S
h
e
re
c
e
iv
e
d
P
h
.
D
.
d
e
g
re
e
in
CS
E
fro
m
JN
TU,
Hy
d
e
ra
b
a
d
,
Tela
n
g
a
n
a
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
5
0
re
se
a
rc
h
p
a
p
e
rs
in
re
fe
re
e
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
l
s,
1
6
re
se
a
rc
h
p
a
p
e
rs
in
c
o
n
fe
re
n
c
e
s
a
n
d
4
p
a
ten
ts.
S
h
e
a
lso
p
u
b
li
sh
e
d
th
re
e
b
o
o
k
s
ti
tl
e
d
D
a
ta
stru
c
tu
re
s
a
n
d
a
lg
o
r
it
h
m
s
u
sin
g
C,
Th
e
e
ra
o
f
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
a
n
d
AI
a
p
p
l
ica
ti
o
n
s.
He
r
a
re
a
s
o
f
re
se
a
rc
h
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
g
ri
d
c
o
m
p
u
ti
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
srik
a
la_
c
se
@m
g
it
.
a
c
.
in
.
Pu
ll
u
r
i
S
r
i
n
iv
a
s
Ra
o
is
P
ro
fe
ss
o
r
a
n
d
He
a
d
,
De
p
a
rtme
n
t
o
f
CS
E
in
Ja
y
a
m
u
k
h
i
In
stit
u
te
o
f
Tec
h
n
o
lo
g
ica
l
S
c
ien
c
e
s,
Tela
n
g
a
n
a
In
d
ia.
He
re
c
e
iv
e
d
h
is
P
h
.
D
.
fro
m
th
e
Un
i
v
e
rsity
o
f
JN
TUK
i
n
Ne
two
r
k
S
e
c
u
ri
ty
.
He
h
a
s
m
o
re
t
h
a
n
2
2
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
h
a
d
p
u
b
li
sh
e
d
m
o
re
th
a
n
5
6
p
a
p
e
rs
in
re
p
u
ted
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
jo
u
r
n
a
ls
.
He
h
a
d
a
tt
e
n
d
e
d
m
a
n
y
wo
rk
s
h
o
p
s,
c
o
n
fe
re
n
c
e
s a
n
d
p
re
se
n
ted
v
a
rio
u
s res
e
a
rc
h
p
a
p
e
rs at
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
His
a
re
a
s
o
f
i
n
ter
e
st
in
c
lu
d
e
n
e
two
r
k
se
c
u
rit
y
,
s
o
ftwa
re
e
n
g
i
n
e
e
rin
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
m
a
c
h
in
e
le
a
rn
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s
rit
h
a
n
ra
o
@
g
m
a
il
.
c
o
m
.
Na
ll
a
S
h
irisha
wo
rk
in
g
a
s
As
so
c
iate
P
ro
fe
ss
o
r,
CS
E
De
p
a
rtme
n
t
a
t
M
LR
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Hy
d
e
ra
b
a
d
,
In
d
i
a
.
S
h
e
re
c
e
iv
e
d
th
e
B.
Tec
h
in
CS
E
in
2
0
0
9
a
n
d
M
.
Tec
h
in
S
o
ftwa
re
En
g
in
e
e
rin
g
i
n
2
0
1
2
.
In
2
0
2
1
,
re
c
e
iv
e
d
th
e
P
h
.
D.
d
e
g
re
e
in
F
a
c
u
l
ty
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
fro
m
K
LU,
Vijay
a
wa
d
a
,
An
d
h
ra
P
ra
d
e
sh
,
I
n
d
ia.
S
h
e
h
a
s
1
3
y
e
a
rs
o
f
e
x
p
e
rien
c
e
i
n
tea
c
h
i
n
g
a
n
d
1
.
5
y
e
a
rs
in
re
se
a
rc
h
.
S
h
e
p
u
b
li
sh
e
d
2
0
p
u
b
li
c
a
ti
o
n
s
in
jo
u
rn
a
ls,
p
u
b
li
c
a
ti
o
n
s
in
c
o
n
fe
re
n
c
e
s
a
n
d
5
p
a
ten
ts.
Re
se
a
rc
h
in
tere
st
in
c
l
u
d
e
s
d
a
ta
m
in
i
n
g
,
in
f
o
rm
a
ti
o
n
se
c
u
rit
y
,
n
e
tw
o
rk
se
c
u
rit
y
,
b
ig
d
a
ta
a
n
a
ly
ti
c
s
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
a
ll
a
sh
iri
sh
a
@m
lri
n
stit
u
ti
o
n
s.a
c
.
in
.
G
u
n
n
a
m
S
r
in
i
v
a
s
c
u
rre
n
tl
y
wo
rk
i
n
g
a
s
As
sista
n
t
P
ro
fe
ss
o
r
i
n
th
e
D
e
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
Ad
it
y
a
En
g
i
n
e
e
rin
g
Co
ll
e
g
e
,
S
u
ra
m
p
a
le
m
,
Ka
k
in
a
d
a
,
A.
P
,
I
n
d
ia.
His
a
re
a
s
o
f
i
n
tere
st
a
re
d
a
ta
m
in
i
n
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
e
e
p
lea
rn
in
g
.
He
h
a
s
p
u
b
li
sh
e
d
re
se
a
rc
h
p
a
p
e
rs
in
v
a
ri
o
u
s
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
rn
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
srin
iv
a
s.g
@a
d
it
y
a
u
n
i
v
e
rsity
.
i
n
.
Dr
.
Er
r
y
S
r
e
e
d
e
v
i
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
P
ro
fe
ss
o
r
a
n
d
HO
D,
D
e
p
a
rtme
n
t
o
f
M
CA,
S
ri
Ve
n
k
a
tes
wa
ra
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Ti
r
u
p
a
ti
.
S
h
e
c
o
m
p
lete
d
h
e
r
M
CA
fro
m
JN
TUH
a
n
d
Ph
.
D
.
fro
m
S
V
Un
i
v
e
rsity
,
Ti
r
u
p
a
ti
.
S
h
e
is
h
a
v
i
n
g
1
7
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
S
h
e
p
u
b
li
sh
e
d
2
5
re
se
a
rc
h
p
a
p
e
rs
in
re
p
u
te
d
jo
u
rn
a
ls,
a
tt
e
n
d
e
d
1
5
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
1
2
F
DPs.
He
r
a
re
a
s
o
f
in
tere
st
a
re
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
n
e
two
rk
se
c
u
rit
y
,
a
n
d
d
a
ta
sc
ien
c
e
.
S
h
e
is
a
m
e
m
b
e
r
o
f
CS
TA.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sre
e
d
e
v
i.
m
c
a
1
5
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.